TW201915830A - Information recognition method and apparatus, and electronic device - Google Patents
Information recognition method and apparatus, and electronic device Download PDFInfo
- Publication number
- TW201915830A TW201915830A TW107119428A TW107119428A TW201915830A TW 201915830 A TW201915830 A TW 201915830A TW 107119428 A TW107119428 A TW 107119428A TW 107119428 A TW107119428 A TW 107119428A TW 201915830 A TW201915830 A TW 201915830A
- Authority
- TW
- Taiwan
- Prior art keywords
- target object
- historical
- current target
- detection result
- same
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/30—Scenes; Scene-specific elements in albums, collections or shared content, e.g. social network photos or video
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
Description
本申請實施例涉及電腦應用技術領域,尤其涉及一種資訊識別方法、裝置及電子設備。The embodiments of the present application relate to the field of computer application technology, and in particular, to an information identification method, device, and electronic device.
在現今的考勤、門禁、監控等應用領域中,均涉及快速確認人員身份的需求,而目前通常利用人體的生物特徵來進行身份認證,其中,人臉識別應用的最為廣泛。 人臉識別是基於人的臉部特徵進行身份識別的一種生物識別技術,人臉識別首先需要進行人臉檢測,以確定人臉,之後再對檢測獲得的人臉進行人臉識別,以考勤應用為例,考勤系統通過對採集的影像進行檢測,可以確定影像中是否包括人臉;基於檢測到的人臉,從已登記的員工資料庫中進行人臉識別,以確定該人臉對應的員工資訊,實現身份確認的目的。 由於影像採集通常一直進行,針對每一幀影像均會進行人臉識別,而相鄰的幾幀影像可能均是針對同一個使用者採集獲得,這就會導致重複工作,而影響識別的效率。In today's application areas such as attendance, access control, monitoring, etc., all involve the need to quickly confirm the identity of a person. Currently, the biological characteristics of the human body are usually used for identity authentication. Among them, face recognition is the most widely used. Face recognition is a kind of biometric recognition technology based on the facial features of a person. Face recognition first needs to perform face detection to determine the face, and then perform face recognition on the detected face to apply for time and attendance. As an example, the time and attendance system can determine whether a face is included in the image by detecting the captured image; based on the detected face, perform face recognition from the registered employee database to determine the employee corresponding to the face Information to achieve the purpose of identity verification. Because image collection is usually performed all the time, face recognition is performed for each frame of images, and adjacent frames of images may be acquired for the same user, which will cause repeated work and affect the efficiency of recognition.
本申請實施例提供一種資訊識別方法、裝置及電子設備,用以解決現有技術中識別效率較低的技術問題。 第一方面,本申請實施例中提供了一種資訊識別方法,包括: 對採集獲得的影像進行檢測,以獲得至少一個當前目標對象; 確定所述至少一個當前目標對象是否與歷史檢測結果中的歷史目標對象相同; 對與歷史檢測結果中的歷史目標對象不同的當前目標對象進行識別。 可選地,還包括: 對與歷史檢測結果中的歷史目標對象相同的當前目標對象不進行識別。 可選地,所述確定所述至少一個當前目標對象是否與歷史檢測結果中的歷史目標對象相同包括: 確定任一當前目標對象所在位置區域與歷史檢測結果中的任一歷史目標對象所在位置區域是否一致,若是,確定所述任一當前目標對象與所述任一歷史目標對象相同,否則,確定所述任一當前目標對象與所述任一歷史目標對象不同。 可選地,所述對與歷史檢測結果中的歷史目標對象相同的當前目標對象不進行識別包括: 獲取任一當前目標對象以及歷史檢測結果中與所述任一當前目標對象相同的任一歷史目標對象的對象特徵; 確定所述任一當前目標對象的對象特徵是否和與其相同的所述任一歷史目標對象的對象特徵相同; 如果是,對所述任一當前目標對象不進行識別; 如果否,對所述任一當前目標對象進行識別。 可選地,所述確定所述至少一個當前目標對象是否與歷史檢測結果中的歷史目標對象相同包括: 分別獲取所述至少一個當前目標對象的對象特徵; 確定歷史檢測結果中,是否存在對象特徵與所述至少一個當前目標對象的對象特徵相同的歷史目標對象。 可選地,所述對與歷史檢測結果中的歷史目標對象相同的當前目標對象不進行識別包括: 確定歷史檢測結果中,與任一當前目標對象相同的歷史目標對象是否識別成功; 如果是,對所述任一當前目標對象不進行識別; 如果否,對所述任一當前目標對象進行識別。 可選地,所述確定任一當前目標對象所在位置區域與歷史檢測結果中的任一歷史目標對象所在位置區域是否一致包括: 確定任一當前目標對象所在位置區域與歷史檢測結果中的任一歷史目標對象所在位置區域的位置偏移是否在預設範圍。 可選地,所述目標對象為人臉。 第二方面,本申請實施例中提供了一種資訊識別裝置,包括: 檢測模組,用於對採集獲得的影像進行檢測,以獲得至少一個當前目標對象; 判斷模組,用於確定所述至少一個當前目標對象是否與歷史檢測結果中的歷史目標對象相同; 第一識別模組,用於對與歷史檢測結果中的歷史目標對象不同的當前目標對象進行識別。 可選地,還包括: 第二識別模組,用於對與歷史檢測結果中的歷史目標對象相同的當前目標對象不進行識別。 可選地,所述判斷模組具體用於: 確定任一當前目標對象所在位置區域與歷史檢測結果中的任一歷史目標對象所在位置區域是否一致,若是,確定所述任一當前目標對象與所述任一歷史目標對象相同,否則,確定所述任一當前目標對象與所述任一歷史目標對象不同。 可選地,所述第二識別模組具體用於獲取任一當前目標對象以及歷史檢測結果中與所述任一當前目標對象相同的任一歷史目標對象的對象特徵;確定所述任一當前目標對象的對象特徵是否和與其相同的所述任一歷史目標對象的對象特徵相同;如果是,對所述任一當前目標對象不進行識別;如果否,對所述任一當前目標對象進行識別。 可選地,所述判斷模組具體用於:分別獲取所述至少一個當前目標對象的對象特徵;確定歷史檢測結果中,是否存在對象特徵與所述至少一個當前目標對象的對象特徵相同的歷史目標對象。 可選地,所述第二識別模組具體用於確定歷史檢測結果中,與任一當前目標對象相同的歷史目標對象是否識別成功;如果是,對所述任一當前目標對象不進行識別;如果否,對所述任一當前目標對象進行識別。 可選地,所述判斷模組具體用於:確定任一當前目標對象所在位置區域與歷史檢測結果中的任一歷史目標對象所在位置區域的位置偏移是否在預設範圍。 協力廠商面,本申請實施例中提供了一種電子設備,包括處理組件,以及分別與所述處理組件連接的記憶體; 所述記憶體儲存一條或多條電腦程式指令,所述一條或多條電腦程式指令供所述處理組件調用並執行; 所述處理組件用於: 對採集獲得的影像進行檢測,以確定至少一個當前目標對象; 確定所述至少一個當前目標對象是否與歷史檢測結果中的歷史目標對象相同; 對與歷史檢測結果中的歷史目標對象不同的當前目標對象進行識別。 可選地,還包括與所述處理組件連接的採集組件,用於採集影像; 所述處理組件對採集獲得的影像進行檢測,以確定至少一個當前目標對象具體是對所述採集組件採集獲得影像進行檢測,以確定至少一個當前目標對象。 本申請實施例中,對採集獲得的影像進行檢測,以確定至少一個當前目標對象;確定所述至少一個當前目標對象是否與歷史檢測結果中的目標對象相同;僅對與歷史檢測結果中的目標對象不同的當前目標對象進行識別, 因此可以減少識別時間,提高識別效率。 本申請的這些方面或其他方面在以下實施例的描述中會更加簡明易懂。The embodiments of the present application provide an information identification method, device, and electronic device to solve the technical problem of low identification efficiency in the prior art. In a first aspect, an embodiment of the present application provides an information recognition method, including: detecting acquired images to obtain at least one current target object; determining whether the at least one current target object is related to a history in a historical detection result The target object is the same; 识别 Identify the current target object that is different from the historical target object in the historical detection result. Optionally, it further includes: 不 Does not recognize the current target object that is the same as the historical target object in the historical detection result. Optionally, the determining whether the at least one current target object is the same as the historical target object in the historical detection result includes: determining the location area of any current target object and the location area of any historical target object in the historical detection result Whether they are consistent, if yes, determine that any of the current target objects is the same as the any of historical target objects; otherwise, determine that the any of the current target objects are different from the any of the historical target objects. Optionally, not identifying the current target object that is the same as the historical target object in the historical detection result includes: 检测 acquiring any current target object and any history in the historical detection result that is the same as the any current target object The object characteristics of the target object; determining whether the object characteristics of any of the current target objects are the same as the object characteristics of any of the historical target objects that are the same; if so, not identifying any of the current target objects; if No, identify any of the current target objects. Optionally, the determining whether the at least one current target object is the same as the historical target object in the historical detection result includes: 获取 separately obtaining the object characteristics of the at least one current target object; determining whether there are object characteristics in the historical detection result A historical target object with the same object characteristics as the at least one current target object. Optionally, not identifying the current target object that is the same as the historical target object in the historical detection result includes: determining whether the historical target object that is the same as any current target object in the historical detection result is successfully identified; 识别 if yes, Do not identify any of the current target objects; If not, identify any of the current target objects. Optionally, determining whether the location area of any current target object is consistent with the location area of any historical target object in the historical detection results includes: determining any of the location area of any current target object and the historical detection result Whether the position offset of the location area of the historical target object is within a preset range. Optionally, the target object is a human face. In a second aspect, an embodiment of the present application provides an information identification device, including: a detection module for detecting an acquired image to obtain at least one current target object; a determination module for determining the at least one Whether a current target object is the same as the historical target object in the historical detection result; a first recognition module for identifying a current target object different from the historical target object in the historical detection result. Optionally, it further includes: A second recognition module, configured to not identify a current target object that is the same as the historical target object in the historical detection result. Optionally, the judgment module is specifically configured to: determine whether the location area of any current target object is consistent with the location area of any historical target object in the historical detection result, and if so, determine whether the current target object and The any historical target object is the same; otherwise, it is determined that the any current target object is different from the any historical target object. Optionally, the second recognition module is specifically configured to obtain any current target object and an object feature of any historical target object that is the same as the current target object in the historical detection result; determine the any current target object Whether the object characteristic of the target object is the same as the object characteristic of any of the historical target objects that are the same; if it is, the current target object is not identified; if not, the current target object is identified . Optionally, the judging module is specifically configured to: obtain object characteristics of the at least one current target object separately; determine whether there is a history in the historical detection result that the object characteristics are the same as the object characteristics of the at least one current target object target. Optionally, the second recognition module is specifically configured to determine whether a historical target object that is the same as any current target object in the historical detection result is successfully identified; if so, the current target object is not identified; If not, identify any of the current target objects. Optionally, the judgment module is specifically configured to determine whether a position offset between a location area of any current target object and a location area of any historical target object in historical detection results is within a preset range. For the third party, an electronic device is provided in the embodiment of the present application, which includes a processing component and a memory connected to the processing component, respectively. The memory stores one or more computer program instructions, the one or more instructions. Computer program instructions for the processing component to call and execute; the processing component is used to: 检测 detect acquired images to determine at least one current target object; determine whether the at least one current target object is in line with historical detection results The historical target object is the same; 识别 Identify the current target object that is different from the historical target object in the historical detection result. Optionally, it further includes an acquisition component connected to the processing component for acquiring images; the processing component detects the acquired images to determine that at least one current target object specifically acquires images from the acquisition component Detection is performed to determine at least one current target object. In the embodiment of the present application, the acquired image is detected to determine at least one current target object; it is determined whether the at least one current target object is the same as the target object in the historical detection result; only the target in the historical detection result is detected. The current target object with different objects is recognized, so the recognition time can be reduced and the recognition efficiency can be improved.方面 These or other aspects of this application will be more concise and easy to understand in the description of the following embodiments.
為了使本技術領域的人員更好地理解本申請方案,下面將結合本申請實施例中的附圖,對本申請實施例中的技術方案進行清楚、完整地描述。 在本申請的說明書和申請專利範圍及上述附圖中的描述的一些流程中,包含了按照特定順序出現的多個操作,但是應該清楚瞭解,這些操作可以不按照其在本文中出現的順序來執行或並存執行,操作的序號如101、102等,僅僅是用於區分開各個不同的操作,序號本身不代表任何的執行順序。另外,這些流程可以包括更多或更少的操作,並且這些操作可以按循序執行或並存執行。需要說明的是,本文中的“第一”、“第二”等描述,是用於區分不同的消息、設備、模組等,不代表先後順序,也不限定“第一”和“第二”是不同的類型。 本申請實施例的技術方案可以應用於考勤、門禁、監控、安防等安全領域中,用於身份識別,本申請實施例中的目標對象可以為人臉,當然也不排除可以為人體的其它生物特徵。與人臉識別過程類似,針對目標對象的識別同樣首先需要進行檢測,以確定目標對象,再對檢測獲得的目標對象進行識別,以對目標對象進行身份確認。 通過本申請實施例的技術方案可以減少識別時間,提高識別效率,特別是適用於針對多個目標對象同時進行識別的場景中。 以人臉識別為例,正如背景技術中所述,在人臉識別過程中,影像採集一直進行,人臉檢測可以針對每一幀影像進行,而短時間內,通常數百毫秒,採集對象也即使用者的位置變化通常不大,也即相鄰幾幀影像可能均為採集同一個或者同一批使用者而獲得的。現有技術中,對每一幀影像均會進行人臉檢測以及人臉識別,但是,可能檢測出的人臉已經識別成功,因此會造成重複識別,從而增加了識別時間,降低了識別效率。 為了提高識別效率,發明人經過一系列研究發現,由於識別過程非常複雜,以人臉識別為例,例如需要首先提取人臉特徵構造人臉特徵範本,再從資料庫中儲存的各個人臉特徵範本中進行比對,以確定該人臉特徵範本對應的身份資訊,完成身份認證,那麼如果可以減少人臉識別時間,則可以大大提高識別效率。 據此,提出了本申請的技術方案,在本申請實施例中,對採集獲得的影像進行檢測,以確定至少一個當前目標對象;確定所述至少一個當前目標對象是否與歷史檢測結果中的目標對象相同;僅對與歷史檢測結果中的目標對象不同的當前目標對象進行識別,因此可以減少識別時間,提高識別效率,特別是當存在多個目標對象同時需要進行識別時,將顯著提高識別效率。 下面將結合本申請實施例中的附圖,對本申請實施例中的技術方案進行清楚、完整地描述,顯然,所描述的實施例僅僅是本申請一部分實施例,而不是全部的實施例。基於本申請中的實施例,本領域技術人員在沒有作出創造性勞動前提下所獲得的所有其他實施例,都屬於本申請保護的範圍。 圖1是本申請實施例提供的一種資訊識別方法一個實施例的流程圖,該方法可以包括以下幾個步驟: 101:對採集獲得的影像進行檢測,以獲得至少一個當前目標對象。 為了方便描述,將從採集獲得的影像檢測出的目標對象命名為“當前目標對象”。針對每一次採集獲得的影像均可以按照本申請的技術方案進行處理。 對採集獲得的影像進行檢測,可以獲得當前檢測結果,該當前檢測結果中包括至少一個當前目標對象。 其中,目標對象為人臉時,也即對採集獲得的影像進行人臉檢測,通過人臉檢測可以識別獲得影像中的人臉。 從影像中提取目標對象的演算法可以有多種,例如可以包括基於長條圖粗分割和奇異值特徵的檢測演算法、基於小波變換的檢測演算法、Adaboost演算法等,其基本過程可以是利用樣本影像訓練分類器,以實現目標對象的檢測等,與現有技術相同,在此不再贅述。 在一個實際應用中,影像中可以包括多個目標對象。 102:確定所述至少一個當前目標對象是否與歷史檢測結果中的歷史目標對象相同。 為了方便描述,將歷史檢測結果中的目標對象命名為“歷史目標對象”。 歷史檢測結果通過對歷史採集獲得的影像進行檢測獲得。 其中,該歷史檢測結果可以具體是指前一次檢測結果,也即是對前一次採集獲得的影像進行檢測獲得。 本實施例中,將當前檢測結果以及歷史檢測結果進行比較,判斷任一當前目標對象是否與歷史檢測結果中的任一歷史目標對象相同。 其中,判斷目標對象是否相同可以有多種實現方式,在下面實施例中會詳細進行介紹。 103:將與歷史檢測結果中的歷史目標對象不同的當前目標對象進行識別。 與歷史檢測結果中的歷史目標對象相同的當前目標對象即不進行識別。也即本實施例中僅對與歷史檢測結果中的歷史目標對象不同的當前目標對象進行識別。 可選地,對於與歷史檢測結果中的歷史目標對象相同的當前目標對象則繼續進行識別。 其中,對當前目標對象進行識別例如可以包括提取當前目標對象的對象特徵,將提取獲得的人臉特徵與資料庫中儲存的特徵範本進行搜索匹配,計算範本相似度,如果相似度大於第一預定值,則可以確定該當前目標對象識別通過,該特徵範本對應的身份資訊即為該當前目標對象的身份資訊;如果相似度小於第二預定值,則可以確定該當前目標對象識別未通過,如果相似度小於第一預定值或者大於第二預定值,則可以確定該當前目標對象識別失敗,無法識別該當前目標對象的身份資訊,需要重新進行識別等。 通過本實施例,僅對與歷史檢測結果中的任一歷史目標對象不同的任一當前目標對象進行識別,而如果任一當前目標對象與歷史檢測結果中的任一歷史目標對象相同,表明該當前目標對象已經進行了識別,則可以無需再進行識別,以減少識別時間,提高識別效率。 其中,作為一種可能的實現方式,所述確定所述至少一個當前目標對象是否與歷史檢測結果中的歷史目標對象相同可以包括: 分別獲取所述至少一個當前目標對象的對象特徵; 確定歷史檢測結果中,是否存在對象特徵與所述至少一個當前目標對象的對象特徵相同的歷史目標對象。 該對象特徵可以為粗細微性特徵,採用特徵提取演算法提取獲得,對象特徵通常採用多維向量資料表示,其維度可以低於識別過程提取的對象特徵的維度。 特徵提取演算法例如可以LBP(Local Binary Patterns,局部二值模式)、基於幾何特徵的方法、基於統計特徵的方法等,與現有技術相同,在此不再贅述。 作為另一種可能的實現方式,由於對象檢測可以針對每一幀影像進行,而對相鄰兩幀影像的檢測間隔很短,通常數十毫秒,因此,即便使用者處於移動狀態,使用者的位置變化也不會不大,因此可以通過位置比對的方式判斷前後兩次檢測結果中的目標對象是否為同一個目標對象。如圖2所示,是本申請實施例提供的一種資訊識別方法又一個實施例的流程圖,該方法可以包括以下幾個步驟: 201:對採集獲得的影像進行檢測,以獲得至少一個當前目標對象。 202:確定任一當前目標對象所在位置區域與歷史檢測結果中的任一歷史目標對象所在位置區域是否一致,如果是,執行步驟203,如果否,執行步驟204。 本實施例中,該歷史檢測結果具體是指前一次檢測結果。 由於影像採集一直進行,使用者位於採集設備的採集範圍內時,採集設備即可以自動搜索並拍攝包含使用者的影像,在需要進行人臉識別,即拍攝使用者的人臉影像。 可選地,可以是判斷任一當前目標對象所在位置區域與歷史檢測結果中的任一歷史目標對象所在位置區域的位置偏移是否在預設範圍。 其中,目標對象所在位置區域可以以目標對象中預設特徵點的位置座標表示,以目標對象為人臉為例,該預設特徵點例如可以是人臉中的左眼或者右眼、鼻子、嘴巴等。 為了保證識別準確度,還可以判斷當前檢測時間與歷史檢測時間的時間差是否在允許範圍內,若是,再判斷任一當前目標對象所在位置區域與歷史檢測結果中的任一歷史目標對象所在位置區域是否一致;否則,則對該至少一個當前目標對象直接進行識別。 203:確定所述任一當前目標對象與歷史檢測結果中的所述任一歷史目標對象相同。 204:確定所述任一當前目標對象與歷史檢測結果中的所述任一歷史目標對象不同。 205:對與歷史檢測結果中的歷史目標對象相同的當前目標對象不進行識別。 206:對與歷史檢測結果中的歷史目標對象不同的當前目標對象進行識別。 也即僅將與歷史檢測結果中的各個目標對象均不同的當前目標對象進行識別。 本實施例中,通過位置比對的方式可以確定前後兩次檢測結果中的目標對象是否相同,從而針對相同的目標對象可以無需進行識別,則僅對不同的目標對象進行識別,通過減少識別時間,以縮短識別時間,提高識別效率。 其中,為了保證識別準確度,在某些實施例中,所述對與歷史檢測結果中的歷史目標對象相同的當前目標對象不進行識別可以包括: 獲取任一當前目標對象以及歷史檢測結果中與所述任一當前目標對象相同的任一歷史目標對象的對象特徵; 確定所述任一當前目標對象的對象特徵是否與所述任一歷史目標對象的對象特徵相同; 如果是,對所述任一當前目標對象不進行識別; 如果否,對所述任一當前目標對象進行識別。 也即針對任一當前目標對象以及歷史檢測結果中與所述任一當前目標對象相同的任一歷史目標對象,結合對象特徵進一步的進行驗證。 該對象特徵可以為粗略特徵,採用特徵提取演算法提取獲得,對象特徵通常採用多維向量資料表示,其維度可以低於識別過程提取的對象特徵的維度。 特徵提取演算法例如可以為LBP演算法、基於幾何特徵的方法、基於統計特徵的方法等,與現有技術相同,在此不再贅述。 此外,結合上文描述可知,對目標對象進行識別獲得的識別結果可以包括識別成功或者識別失敗,識別成功包括識別通過或者識別未通過,識別通過也即資料庫中存在目標對象對應的身份資訊, 也即該目標對象的對象特徵與資料庫中的特徵範本的相似度大於第一預定值;識別未通過可以認為資料庫中不存在目標對象對應的身份資訊,也即該目標對象的對象特徵與資料庫中的特徵範本的相似度小於第二預定值。識別失敗表明無法確認目標對象的身份資訊,需要重新進行識別。 因此,如果歷史檢測結果中,與當前目標對象相同的歷史目標對象識別失敗,則該當前目標對象也需要重新進行識別,以識別該當前目標對象的身份資訊,因此為了進一步保證識別準確度,在某些實施例中,所述對與歷史檢測結果中的歷史目標對象相同的當前目標對象不進行識別可以包括: 確定歷史檢測結果中,與任一當前目標對象相同的歷史目標對象是否識別成功; 如果是,對所述任一當前目標對象不進行識別; 如果否,對所述任一當前目標對象進行識別。 其中,可選地, 為了方便識別,可以對識別成功的目標對象設置識別成功標記,因此所述判斷歷史檢測結果中,與任一當前目標對象相同的歷史目標對象是否識別成功可以是: 確定歷史檢測結果中,與任一當前目標對象相同的歷史目標對象是否設置有識別成功標記。 因此,對所述任一當前目標對象進行識別之後,可以基於識別結果,將識別成功的當前目標對象設置識別成功標記。 此外,為了進一步提高識別便利性,在某些實施例中,所述對與歷史檢測結果中的歷史目標對象相同的當前目標對象不進行識別可以包括: 為所述至少一個當前目標對象設置不同對象編號,其中,當前檢測結果與歷史檢測結果中相同的目標對象的對象編號相同; 對對象編號與歷史檢測結果中的歷史目標對象的對象編號相同的當前目標對象不進行識別。 其中,如果歷史檢測結果中,與任一當前目標對象的對象編號相同的歷史目標對象設置有識別成功標記,則即可以對所述任一當前目標對象不進行識別。 本申請實施例中的技術方案,可以應用於考勤、門禁等應用領域中,當然也適用於證件中的身份識別、重要場所中的安全檢測和監控、智慧卡中的身份識別、電腦登錄等網路安全控制等多種不同的安全領域。 其中,在實際應用中,本申請實施例中所述的目標對象可以具體即是指人臉,下面以目標對象為人臉為例,對本申請的技術方案進行描述。 如圖3所示,為本申請實施例提供的一種資訊識別方法又一個實施例的流程圖,該方法可以包括以下幾個步驟: 301:對採集獲得的影像進行人臉檢測,以獲得至少一個當前人臉。 302:確定任一當前人臉所在位置區域與前一次檢測結果中的任一歷史人臉所在位置區域是否一致,如果是執行步驟303,如果否,執行步驟304。 可選地,可以是判斷任一當前人臉所在位置區域與前一次檢測結果中的任一歷史人臉所在位置區域的位置偏移是否在預設範圍。 其中,人臉所在位置區域可以是指人臉中某一預設特徵點的位置座標,例如該預設特徵點可以為嘴巴、鼻子、左眼或者右眼等。 303:確定所述任一當前人臉與前一次檢測結果中的所述任一歷史人臉相同,並執行步驟305。 304:確定所述任一當前人臉與前一次檢測結果中的所述任一歷史人臉不同,並執行步驟309。 305:分別獲取所述任一當前人臉以及所述任一歷史人臉的臉部特徵。 其中,臉部特徵提取例如可以採用LBP演算法實現。 306:確定所述任一當前人臉的臉部特徵是否與所述任一歷史人臉的臉部特徵相同;如果是,執行步驟307,如果否,執行步驟309。 可選地,可以為各個當前人臉設置不同的人臉編號,保證與前一次檢測結果中的任一歷史人臉相同的一當前人臉設置與所述任一歷史人臉相同的人臉編號。 307:確定所述任一歷史人臉是否設置有識別成功標記,如果是,執行步驟308,如果否,執行步驟309。 308:對所述任一當前人臉不進行識別。 309:對所述任一當前人臉進行人臉識別。 310:基於識別結果,將識別成功的各個當前人臉設置識別成功標記。 本實施例中,在人臉識別過程中,基於前一次檢測結果,如果存在與當前人臉相同的歷史人臉,則可以表明該當前人臉已經經過識別,因此可以無需再次進行識別,從而可以減少識別時間,減少人臉識別時間,提高人臉識別效率。 其中,本申請實施例的技術方案可以應用於資訊識別系統中作為一個實施例,如圖4中所示,該資訊識別系統可以包括採集終端401以及認證伺服器402; 採集終端401用於採集影像,並將影像發送至認證伺服器402;由認證伺服器402對採集獲得的影像進行檢測,以獲得至少一個當前目標對象;確定所述至少一個當前目標對象是否與歷史檢測結果中的歷史目標對象相同;對與歷史檢測結果中的歷史目標對象相同的當前目標對象不進行識別;而僅對與歷史檢測結果中的歷史目標對象不同的當前目標對象進行識別。 也即由採集終端401實現影像採集,由認證伺服器實現對象檢測以及對象識別過程。 採集終端可以針對位於其採集範圍內的多個使用者進行影像採集,從而可以從影像中檢測獲得多個目標對象,該目標對象可以為使用者的人臉。 作為又一個實施例,如圖5中所示,該資訊識別系統可以包括檢測終端501以及認證伺服器502; 檢測終端501用於採集影像,並對採集獲得的影像進行檢測,以獲得至少一個當前目標對象,並將所述至少一個當前目標對象發送至認證伺服器;確定所述至少一個當前目標對象是否與歷史檢測結果中的歷史目標對象相同;觸發認證伺服器502將與歷史檢測結果中的歷史目標對象相同的當前目標對象不進行識別;以及觸發認證伺服器502將與歷史檢測結果中的歷史目標對象不同的當前目標對象進行識別。 也即由檢測終端實現影像採集以及對象檢測,由認證伺服器實現對象識別,以保證檢測終端以及認證伺服器的處理性能。 當然,本申請實施例的技術方案也可以應用於獨立的識別終端中,由識別終端完成影像採集、對象檢測以及對象識別等操作。 在一個實際應用中,上述的採集終端、檢測終端或者識別終端可以分別實現為具有不同功能的考勤機,以實現考勤目的。 在考勤應用中,確定目標對象對應身份資訊之後,即可以對應該身份資訊記錄考勤時間等。 圖6為本申請實施例提供的一種資訊識別裝置一個實施例的結構示意圖,其中,該裝置可以配置在如圖4所示的認證伺服器中,也可以配置在如圖5所示的檢測終端中,當然也可以配置在識別終端中。 該裝置可以包括: 檢測模組601,用於對採集獲得的影像進行檢測,以確定至少一個當前目標對象。 判斷模組602,用於確定所述至少一個當前目標對象是否與歷史檢測結果中的歷史目標對象相同; 第一識別模組603,用於將與歷史檢測結果中的歷史目標對象不同的當前目標對象進行識別。 此外,可選地,如圖7中所示,與圖6所示裝置不同之處在於,該裝置還可以包括: 第二識別模組604,用於對與歷史檢測結果中的歷史目標對象相同的當前目標對象進行識別。 通過本實施例,僅對與歷史檢測結果中的任一歷史目標對象不同的任一當前目標對象進行識別,而如果任一當前目標對象與歷史檢測結果中的任一歷史目標對象相同,表明該當前目標對象已經進行了識別,則可以無需再進行識別,以減少識別時間,提高識別效率。 作為一種可能的實現方式,所述判斷模組可以具體用於:分別獲取所述至少一個當前目標對象的對象特徵;確定歷史檢測結果中,是否存在對象特徵與所述至少一個當前目標對象的對象特徵相同的歷史目標對象。 作為另一種可能的實現方式,所述判斷模組可以具體用於: 確定任一當前目標對象所在位置區域與歷史檢測結果中的任一歷史目標對象所在位置區域是否一致,若是,確定所述任一當前目標對象與所述任一歷史目標對象相同,否則,確定所述任一當前目標對象與所述任一歷史目標對象不同。通過位置比對的方式可以確定前後兩次檢測結果中的目標對象是否相同,從而針對相同的目標對象可以無需進行識別,則僅對不同的目標對象進行識別,通過減少識別時間,以縮短識別時間,提高識別效率。 可選地,所述判斷模組可以具體用於確定任一當前目標對象所在位置區域與歷史檢測結果中的任一歷史目標對象所在位置區域的位置偏移是否在預設範圍。 其中,為了保證識別準確度,在某些實施例中,所述第二識別模組可以具體用於獲取任一當前目標對象以及歷史檢測結果中與所述任一當前目標對象相同的任一歷史目標對象的對象特徵;確定所述任一當前目標對象的對象特徵是否和與其相同的所述任一歷史目標對象的對象特徵相同;如果是,對所述任一當前目標對象不進行識別;如果否,對所述任一當前目標對象進行識別。 也即針對任一當前目標對象以及歷史檢測結果中與所述任一當前目標對象相同的任一歷史目標對象,結合對象特徵進一步的進行驗證。 此外,在某些實施例中,所述第二識別模組可以具體用於確定歷史檢測結果中,與任一當前目標對象相同的歷史目標對象是否識別成功;如果是,對所述任一當前目標對象不進行識別;如果否,對所述任一當前目標對象進行識別。 其中,可選地, 為了方便識別,可以對識別成功的目標對象設置識別成功標記,因此所述第一識別模組判斷歷史檢測結果中,與任一當前目標對象相同的歷史目標對象是否識別成功可以具體是: 判斷歷史檢測結果中,與任一當前目標對象相同的歷史目標對象是否設置有識別成功標記。 因此,所述第二識別模組對所述任一當前目標對象進行識別之後,還可以基於識別結果,將識別成功的當前目標對象設置識別成功標記。 此外,為了進一步提高識別便利性,在某些實施例中,第一識別模組可以具體用於為所述至少一個當前目標對象設置不同對象編號,其中,當前檢測結果與歷史檢測結果中相同的目標對象的對象編號相同; 對對象編號與歷史檢測結果中的歷史目標對象的對象編號相同的當前目標對象不進行識別。 圖6或7所述的資訊識別裝置可以執行圖1~圖3任一實施例所述的資訊識別方法,其實現原理和技術效果不再贅述。對於上述實施例中的資訊識別裝置其中各個模組、單元執行操作的具體方式已經在有關該方法的實施例中進行了詳細描述,此處將不做詳細闡述說明。 在一個可能的設計中,圖6或圖7所示實施例的資訊識別裝置可以實現為一電子設備,如圖8所示,該電子設備可以包括處理組件801,以及分別與所述處理組件801連接的記憶體802; 所述記憶體802儲存一條或多條電腦程式指令,所述一條或多條電腦程式指令供所述處理組件801調用並執行; 所述處理組件801用於: 對採集獲得的影像進行檢測,以確定至少一個當前目標對象; 確定所述至少一個當前目標對象是否與歷史檢測結果中的歷史目標對象相同; 對與歷史檢測結果中的歷史目標對象不同的當前目標對象進行識別。 處理組件801還用於對與歷史檢測結果中的歷史目標對象相同的當前目標對象不進行識別。 處理組件對與歷史檢測結果中的歷史目標對象相同的當前目標對象則不進行識別。 在一個實際應用中,該電子設備可以為與採集終端連接的認證伺服器,該採集終端可以為攝影機等攝像設備。 此外,作為又一個實施例,如圖9中所示,與圖8所示實施例不同之處在於,該電子設備還可以包括與處理組件801連接,用於採集影像的採集組件803。 處理組件801具體是對所述採集組件803採集獲得的影像進行檢測,以確定至少一個當前目標對象。 該實施例中,該電子設備可以為一個獨立的實現影像採集、對象檢測以及對象識別的識別終端。 此外,在某些實施例中,該處理組件801確定的當前目標對象還可以發送至認證伺服器,處理組件801對與歷史檢測結果中的歷史目標對象相同的當前目標對象不進行識別可以是觸發認證伺服器將與歷史檢測結果中的歷史目標對象相同的當前目標對象不進行識別。處理組件801對與歷史檢測結果中的歷史目標對象不同的當前目標對象進行識別具體可以是觸發認證伺服器將與歷史檢測結果中的歷史目標對象不同的當前目標對象進行識別。 其中,處理組件801可以包括一個或多個處理器來執行電腦指令,以完成上述的方法中的全部或部分步驟。當然處理組件也可以為一個或多個應用專用積體電路(ASIC)、數位訊號處理器(DSP)、數位信號處理設備(DSPD)、可程式設計邏輯裝置(PLD)、現場可程式設計閘陣列(FPGA)、控制器、微控制器、微處理器或其他電子元件實現,用於執行上述方法。 記憶體802被配置為儲存各種類型的資料以支援在XX設備的操作。記憶體可以由任何類型的揮發性或非揮發性存放裝置或者它們的組合實現,如靜態隨機存取記憶體(SRAM),電可擦除可程式設計唯讀記憶體(EEPROM),可擦除可程式設計唯讀記憶體(EPROM),可程式設計唯讀記憶體(PROM),唯讀記憶體(ROM),磁記憶體,快閃記憶體,磁片或光碟。 採集組件803可以為攝影機。 當然,電子設備必然還可以包括其他部件,例如輸入/輸出介面、通信組件等。 輸入/輸出介面為處理組件和週邊介面模組之間提供介面,上述週邊介面模組可以是輸出設備、輸入裝置等。 通信組件被配置為便於電子設備和其他設備之間有線或無線方式的通信,例如和認證伺服器進行通信等。 本申請實施例還提供了一種電腦可讀儲存介質,儲存有電腦程式,所述電腦程式被電腦執行時可以實現上述圖1~圖3任一項所示實施例的資訊識別方法。 所屬領域的技術人員可以清楚地瞭解到,為描述的方便和簡潔,上述描述的系統,裝置和單元的具體工作過程,可以參考前述方法實施例中的對應過程,在此不再贅述。 以上所描述的裝置實施例僅僅是示意性的,其中所述作為分離部件說明的單元可以是或者也可以不是物理上分開的,作為單元顯示的部件可以是或者也可以不是物理單元,即可以位於一個地方,或者也可以分佈到多個網路單元上。可以根據實際的需要選擇其中的部分或者全部模組來實現本實施例方案的目的。本領域普通技術人員在不付出創造性的勞動的情況下,即可以理解並實施。 通過以上的實施方式的描述,本領域的技術人員可以清楚地瞭解到各實施方式可借助軟體加必需的通用硬體平臺的方式來實現,當然也可以通過硬體。基於這樣的理解,上述技術方案本質上或者說對現有技術做出貢獻的部分可以以軟體產品的形式體現出來,該電腦軟體產品可以儲存在電腦可讀儲存介質中,如ROM/RAM、磁碟、光碟等,包括若干指令用以使得一台電腦設備(可以是個人電腦,伺服器,或者網路設備等)執行各個實施例或者實施例的某些部分所述的方法。 最後應說明的是:以上實施例僅用以說明本申請的技術方案,而非對其限制;儘管參照前述實施例對本申請進行了詳細的說明,本領域的普通技術人員應當理解:其依然可以對前述各實施例所記載的技術方案進行修改,或者對其中部分技術特徵進行等同替換;而這些修改或者替換,並不使相應技術方案的本質脫離本申請各實施例技術方案的精神和範圍。In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. In the description of this application, the scope of the patent application, and some of the processes described in the above drawings, multiple operations appearing in a particular order are included, but it should be clearly understood that these operations may not follow the order in which they appear in this document. Execution or concurrent execution. The sequence numbers of operations such as 101 and 102 are only used to distinguish different operations. The sequence numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be performed sequentially or concurrently. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent the order, nor do they limit "first" and "second" "Are different types. The technical solution of the embodiment of the present application can be applied to security fields such as time and attendance, access control, monitoring, and security for identity recognition. The target object in the embodiment of the present application may be a human face, and of course, other organisms that may be human bodies are not excluded. feature. Similar to the face recognition process, the recognition of the target object also needs to be detected first to determine the target object, and then the target object obtained by detection is used to confirm the identity of the target object. The technical solution of the embodiment of the present application can reduce the recognition time and improve the recognition efficiency, and is especially applicable to a scenario in which multiple target objects are recognized at the same time. Taking face recognition as an example, as described in the background art, during the face recognition process, image acquisition is always performed, and face detection can be performed for each frame of the image. In a short time, usually hundreds of milliseconds, the acquisition object is also That is, the position of the user usually does not change much, that is, several adjacent frames may be obtained by collecting the same user or the same group of users. In the prior art, face detection and face recognition are performed for each frame of the image. However, the detected faces may have been successfully identified, which may cause repeated recognition, thereby increasing recognition time and reducing recognition efficiency. In order to improve the recognition efficiency, the inventor has discovered through a series of studies that because the recognition process is very complicated, taking face recognition as an example, for example, it is necessary to first extract face features to construct a face feature template, and then to store each face feature from the database The template is compared to determine the identity information corresponding to the face feature template and complete the identity authentication. If the face recognition time can be reduced, the recognition efficiency can be greatly improved. Based on this, the technical solution of the present application is proposed. In the embodiment of the present application, the acquired images are detected to determine at least one current target object, and whether the at least one current target object is related to the target in the historical detection result is determined. The object is the same; only the current target object that is different from the target object in the historical detection result is recognized, so the recognition time can be reduced and the recognition efficiency can be improved, especially when there are multiple target objects that need to be identified at the same time, the recognition efficiency will be significantly improved . The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall into the protection scope of the present application. FIG. 1 is a flowchart of an embodiment of an information identification method provided by an embodiment of the present application. The method may include the following steps: 101: Detect an acquired image to obtain at least one current target object. For the convenience of description, the target object detected from the acquired image is named "current target object". The images obtained for each acquisition can be processed according to the technical solution of this application.检测 Perform detection on the acquired image to obtain the current detection result, where the current detection result includes at least one current target object. Among them, when the target object is a human face, that is, face detection is performed on the acquired image, and the face in the image can be identified through the face detection. There are many algorithms for extracting target objects from images. For example, they can include detection algorithms based on bar graph coarse segmentation and singular value features, detection algorithms based on wavelet transform, and Adaboost algorithms. The basic process can be the use of The sample image trains the classifier to achieve the detection of the target object, etc., which is the same as the prior art, and is not repeated here. In an actual application, the image can include multiple target objects. 102: Determine whether the at least one current target object is the same as the historical target object in the historical detection result. For the convenience of description, the target object in the historical detection results is named "historical target object". Historical detection results are obtained by detecting the images acquired by historical collection. Among them, the historical detection result may specifically refer to the previous detection result, that is, the image obtained by the previous acquisition is detected. In this embodiment, the current detection result and the historical detection result are compared to determine whether any current target object is the same as any historical target object in the historical detection result. Among them, there are multiple ways to determine whether the target objects are the same, which will be described in detail in the following embodiments. 103: Identify a current target object that is different from the historical target object in the historical detection result.相同 The current target object that is the same as the historical target object in the history detection result is not recognized. That is, in this embodiment, only the current target object that is different from the historical target object in the historical detection result is identified. Optionally, continue to identify the current target object that is the same as the historical target object in the historical detection result. The identification of the current target object may include, for example, extracting the object features of the current target object, searching for matching between the extracted facial features and the feature template stored in the database, and calculating the template similarity. If the similarity is greater than the first predetermined Value, it can be determined that the identification of the current target object is passed, and the identity information corresponding to the feature template is the identification information of the current target object; if the similarity is less than a second predetermined value, it can be determined that the identification of the current target object has failed, and If the similarity is less than the first predetermined value or greater than the second predetermined value, it can be determined that the recognition of the current target object fails, the identity information of the current target object cannot be identified, and re-identification is required. With this embodiment, only any current target object that is different from any historical target object in the historical detection result is identified, and if any current target object is the same as any historical target object in the historical detection result, it indicates that the The current target object has been identified, so no further identification is required to reduce the identification time and improve the identification efficiency. Wherein, as a possible implementation manner, determining whether the at least one current target object is the same as the historical target object in the historical detection result may include: 获取 separately obtaining object characteristics of the at least one current target object; determining the historical detection result , Whether there is a historical target object whose object characteristics are the same as those of the at least one current target object. The object features can be coarse and fine features, which are obtained by feature extraction algorithm. The object features are usually represented by multi-dimensional vector data, and their dimensions can be lower than the dimensions of the object features extracted during the recognition process. The feature extraction algorithm can be, for example, LBP (Local Binary Patterns, Local Binary Patterns), a method based on geometric features, a method based on statistical features, and the like, which are the same as those in the prior art, and are not repeated here. As another possible implementation method, because object detection can be performed for each frame of image, and the detection interval between two adjacent frames of image is very short, usually tens of milliseconds, so even if the user is in a mobile state, the position of the user The change will not be great, so you can determine whether the target object in the two previous and subsequent detection results is the same target object by means of position comparison. As shown in FIG. 2, it is a flowchart of still another embodiment of an information identification method provided by an embodiment of the present application. The method may include the following steps: 201: Detect an acquired image to obtain at least one current target. Object. 202: Determine whether the location area of any current target object is consistent with the location area of any historical target object in the historical detection result. If yes, go to step 203; if no, go to step 204. In this embodiment, the historical detection result specifically refers to a previous detection result. Because image acquisition is always performed, when the user is within the acquisition range of the acquisition device, the acquisition device can automatically search for and capture the image containing the user, and when face recognition is needed, that is, the user's face image is captured. Optionally, it may be to determine whether the position offset between the location area of any current target object and the location area of any historical target object in the historical detection result is within a preset range. The location area of the target object may be represented by position coordinates of a preset feature point in the target object. Taking the target object as a human face as an example, the preset feature point may be, for example, a left eye or a right eye, a nose, Mouth wait. In order to ensure the accuracy of the recognition, it is also possible to determine whether the time difference between the current detection time and the historical detection time is within the allowable range. If so, then determine the location area of any current target object and the location area of any historical target object in the historical detection result. Whether they are consistent; otherwise, the at least one current target object is directly identified. 203: It is determined that the any current target object is the same as the any historical target object in a history detection result. 204: It is determined that the any current target object is different from the any historical target object in a historical detection result. 205: The current target object that is the same as the historical target object in the history detection result is not recognized. 206: Identify the current target object that is different from the historical target object in the historical detection result. That is, only the current target object that is different from each target object in the historical detection result is identified. In this embodiment, it is possible to determine whether the target object in the two previous detection results is the same by means of position comparison, so that the same target object may not be identified, and only different target objects are identified. By reducing the recognition time, To shorten the recognition time and improve the recognition efficiency. Wherein, in order to ensure the recognition accuracy, in some embodiments, the non-recognition of the current target object that is the same as the historical target object in the historical detection result may include: obtaining any current target object and the historical detection result and the Object characteristics of any historical target object that is the same as any of the current target objects; determine whether the object characteristics of the any current target object are the same as the object characteristics of the any historical target object; if yes, A current target object is not identified; 否 If not, identify any of the current target objects. That is, for any current target object and any historical target object that is the same as any of the current target objects in the historical detection results, further verification is performed in combination with the object characteristics.对象 The object feature can be a rough feature, which is obtained by feature extraction algorithm. The object feature is usually represented by multi-dimensional vector data, and its dimension can be lower than the dimension of the object feature extracted during the recognition process. The feature extraction algorithm can be, for example, an LBP algorithm, a method based on geometric features, a method based on statistical features, and the like, which are the same as those in the prior art, and are not repeated here. In addition, in combination with the above description, it can be known that the recognition result obtained by identifying the target object may include recognition success or recognition failure, and recognition success includes recognition pass or failure, and the identification pass means that there is identity information corresponding to the target object in the database. That is, the similarity between the object characteristics of the target object and the feature template in the database is greater than the first predetermined value; if the identification fails, the identity information corresponding to the target object does not exist in the database, that is, the object characteristics of the target object and The similarity of the feature templates in the database is less than the second predetermined value. Recognition failure indicates that the identity information of the target object cannot be confirmed and needs to be identified again. Therefore, if the historical target object that is the same as the current target object fails to be identified in the historical detection result, the current target object needs to be identified again to identify the identity information of the current target object. Therefore, in order to further ensure the accuracy of the identification, In some embodiments, not identifying the current target object that is the same as the historical target object in the historical detection result may include: determining whether the historical target object that is the same as any current target object in the historical detection result is successfully identified; If yes, the current target object is not identified; 否 If not, the current target object is identified. Among them, optionally, for the convenience of identification, a recognition success flag may be set on the successfully identified target object. Therefore, in the history detection result, whether the historical target object that is the same as any current target object is successfully identified may be: determine history In the detection result, whether a historical target object that is the same as any current target object is set with a recognition success flag. Therefore, after identifying any of the current target objects, a current target object that has been successfully identified may be set with a recognition success flag based on the recognition result. In addition, in order to further improve the convenience of recognition, in some embodiments, not identifying the current target object that is the same as the historical target object in the historical detection result may include: 设置 setting a different object for the at least one current target object Number, where the current detection result is the same as the object number of the same target object in the historical detection result; The current target object with the same object number as the object number of the historical target object in the historical detection result is not identified. Among them, if a historical target object with the same object number as any current target object is set with a recognition success flag in the historical detection result, then any current target object may not be identified. The technical solutions in the embodiments of the present application can be applied to application fields such as attendance and access control. Of course, it can also be applied to networks such as identification in documents, security detection and monitoring in important places, identification in smart cards, and computer login. Road safety control and many other security areas. Among them, in practical applications, the target object described in the embodiments of the present application may specifically refer to a human face. The following uses the target object as a human face as an example to describe the technical solution of the present application. As shown in FIG. 3, which is a flowchart of another embodiment of an information recognition method according to an embodiment of the present application. The method may include the following steps: 301: Perform face detection on an acquired image to obtain at least one The current face. 302: Determine whether the location area of any current face is consistent with the location area of any historical face in the previous detection result. If yes, go to step 303; if no, go to step 304. Optionally, it may be to determine whether the position offset between the location area of any current face and the location area of any historical face in the previous detection result is within a preset range. For example, the location area of the human face may refer to the position coordinates of a preset feature point in the human face. For example, the preset feature point may be a mouth, a nose, a left eye, or a right eye. 303: Determine that the current face is the same as the historical face in the previous detection result, and execute step 305. 304: It is determined that the current face is different from the historical face in the previous detection result, and step 309 is performed. 305: Obtain facial features of the current face and the historical face separately. Among them, the facial feature extraction can be implemented by, for example, an LBP algorithm. 306: Determine whether the facial features of any of the current faces are the same as the facial features of any of the historical faces; if yes, go to step 307; if no, go to step 309. Optionally, a different face number may be set for each current face to ensure that a current face that is the same as any historical face in the previous detection result is set to the same face number as any of the historical faces . 307: Determine whether a recognition success flag is set on any of the historical faces, and if yes, go to step 308; if no, go to step 309. 308: No recognition is performed on any one of the current human faces. 309: Perform face recognition on any one of the current faces. 310: Based on the recognition result, a recognition success flag is set for each current face that has been successfully recognized. In this embodiment, during the face recognition process, based on the previous detection result, if there is a historical face that is the same as the current face, it can be shown that the current face has been recognized, so it is not necessary to perform recognition again, so Reduce recognition time, reduce face recognition time, and improve face recognition efficiency. The technical solution in the embodiment of the present application can be applied to an information recognition system as an example. As shown in FIG. 4, the information recognition system may include a collection terminal 401 and an authentication server 402. The collection terminal 401 is used to collect images And send the image to the authentication server 402; the authentication server 402 detects the acquired image to obtain at least one current target object; determines whether the at least one current target object is related to the historical target object in the historical detection result The same; the current target object that is the same as the historical target object in the historical detection result is not identified; and only the current target object that is different from the historical target object in the historical detection result is identified. That is, image acquisition is performed by the acquisition terminal 401, and object detection and object recognition processes are performed by the authentication server. The acquisition terminal can perform image acquisition for multiple users located within its acquisition range, so that multiple target objects can be detected from the image, and the target object can be the user's face. As another embodiment, as shown in FIG. 5, the information recognition system may include a detection terminal 501 and an authentication server 502; The detection terminal 501 is used to collect images and detect the acquired images to obtain at least one current Target object, and send the at least one current target object to the authentication server; determine whether the at least one current target object is the same as the historical target object in the historical detection result; and trigger the authentication server 502 to The current target object with the same historical target object is not identified; and the authentication server 502 is triggered to identify the current target object that is different from the historical target object in the historical detection result. That is, the image acquisition and object detection are implemented by the detection terminal, and the object recognition is implemented by the authentication server to ensure the processing performance of the detection terminal and the authentication server. Of course, the technical solution of the embodiment of the present application can also be applied to an independent identification terminal, and the identification terminal performs operations such as image acquisition, object detection, and object recognition. In an actual application, the above-mentioned collection terminal, detection terminal, or identification terminal can be respectively implemented as time attendance machines with different functions to achieve the purpose of attendance. In the time and attendance application, after determining the identity information of the target object, you can record the time and attendance corresponding to the identity information. FIG. 6 is a schematic structural diagram of an embodiment of an information identification device according to an embodiment of the present application. The device may be configured in an authentication server as shown in FIG. 4, or may be configured in a detection terminal as shown in FIG. 5. Of course, it can also be configured in the identification terminal. The device may include: A detection module 601, configured to detect the acquired image to determine at least one current target object. A judging module 602 is configured to determine whether the at least one current target object is the same as a historical target object in a historical detection result; a first identification module 603 is configured to compare a current target that is different from the historical target object in the historical detection result; Objects are identified. In addition, optionally, as shown in FIG. 7, the device is different from the device shown in FIG. 6 in that the device may further include: a second identification module 604 configured to identify the historical target object that is the same as the historical target object in the historical detection result; Recognition of the current target object. With this embodiment, only any current target object that is different from any historical target object in the historical detection result is identified, and if any current target object is the same as any historical target object in the historical detection result, it indicates that the The current target object has been identified, so no further identification is required to reduce the identification time and improve the identification efficiency. As a possible implementation manner, the judging module may be specifically configured to: separately obtain object characteristics of the at least one current target object; and determine whether an object feature and an object of the at least one current target object exist in the historical detection result. Historical target objects with the same characteristics. As another possible implementation manner, the judgment module may be specifically configured to: determine whether the location area of any current target object is consistent with the location area of any historical target object in the historical detection result, and if so, determine the A current target object is the same as the any historical target object, otherwise, it is determined that the any current target object is different from the any historical target object. Position comparison can be used to determine whether the target object in the two previous detection results is the same, so that the same target object can be identified without recognition. Only different target objects are identified, and the recognition time can be shortened to reduce the recognition time. To improve recognition efficiency. Optionally, the judgment module may be specifically configured to determine whether a position offset between a location area of any current target object and a location area of any historical target object in a historical detection result is within a preset range. In order to ensure the recognition accuracy, in some embodiments, the second recognition module may be specifically configured to obtain any current target object and any history in a history detection result that is the same as the any current target object. The object characteristics of the target object; determining whether the object characteristics of any of the current target objects are the same as the object characteristics of any of the historical target objects that are the same; if so, not identifying any of the current target objects; if No, identify any of the current target objects. That is, for any current target object and any historical target object that is the same as any of the current target objects in the historical detection results, further verification is performed in combination with the object characteristics. In addition, in some embodiments, the second identification module may be specifically configured to determine whether a historical target object that is the same as any current target object in the history detection result is successfully identified; if yes, the current target object is identified. The target object is not identified; if not, any one of the current target objects is identified. Among them, optionally, for the convenience of recognition, a recognition success flag may be set on the successfully recognized target object, so the first recognition module judges whether the historical target object that is the same as any current target object in the historical detection result is successfully identified. It can be specifically as follows: Determine whether a historical target object that is the same as any current target object is set with a recognition success flag in the historical detection result. Therefore, after the second recognition module recognizes the current target object, the current target object that has been successfully identified may be set with a recognition success flag based on the recognition result. In addition, in order to further improve the convenience of recognition, in some embodiments, the first recognition module may be specifically configured to set a different object number for the at least one current target object, wherein the current detection result is the same as the historical detection result. The target object has the same object number; 不 The current target object with the same object number as the historical target object in the historical detection result is not identified.资讯 The information recognition device described in FIG. 6 or 7 can execute the information recognition method described in any one of the embodiments of FIG. 1 to FIG. 3, and its implementation principles and technical effects will not be described again. The specific manner in which each module and unit of the information identification device in the foregoing embodiment performs operations has been described in detail in the embodiment of the method, and will not be described in detail here. In a possible design, the information recognition device in the embodiment shown in FIG. 6 or FIG. 7 may be implemented as an electronic device. As shown in FIG. 8, the electronic device may include a processing component 801, and the processing component 801 and the processing component 801 respectively. A connected memory 802; the memory 802 stores one or more computer program instructions for the processing component 801 to call and execute; the processing component 801 is used for: to acquire Detecting images to determine at least one current target object; determining whether the at least one current target object is the same as the historical target object in the historical detection result; 识别 identifying a current target object different from the historical target object in the historical detection result . The processing unit 801 is further configured not to identify the current target object that is the same as the historical target object in the historical detection result. The processing component does not recognize the current target object that is the same as the historical target object in the historical detection result.一个 In an actual application, the electronic device may be an authentication server connected to the acquisition terminal, and the acquisition terminal may be an imaging device such as a camera. In addition, as another embodiment, as shown in FIG. 9, it is different from the embodiment shown in FIG. 8 in that the electronic device may further include an acquisition component 803 connected to the processing component 801 and used to acquire an image. The processing component 801 specifically detects the images acquired by the collection component 803 to determine at least one current target object. In this embodiment, the electronic device may be an independent identification terminal that realizes image collection, object detection, and object recognition. In addition, in some embodiments, the current target object determined by the processing component 801 may also be sent to the authentication server, and the processing component 801 may be a trigger if the current target object that is the same as the historical target object in the historical detection result is not identified. The authentication server does not recognize the current target object that is the same as the historical target object in the historical detection result. The processing component 801 recognizes a current target object different from the historical target object in the historical detection result. Specifically, the processing component 801 may trigger the authentication server to identify a current target object different from the historical target object in the historical detection result. Wherein, the processing component 801 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), and field programmable gate arrays. (FPGA), controller, microcontroller, microprocessor, or other electronic components to perform the methods described above. The memory 802 is configured to store various types of data to support operation on the XX device. Memory can be implemented by any type of volatile or non-volatile storage device or a combination of them, such as static random access memory (SRAM), electrically erasable programmable programmable read-only memory (EEPROM), erasable Programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The radon acquisition component 803 may be a camera. Of course, the electronic device must also include other components, such as input / output interfaces, communication components, and so on. The input / output interface provides an interface between the processing component and a peripheral interface module. The peripheral interface module may be an output device, an input device, and the like. The communication component is configured to facilitate wired or wireless communication between the electronic device and other devices, such as communicating with an authentication server.实施 The embodiment of the present application further provides a computer-readable storage medium storing a computer program, and the computer program can implement the information identification method of the embodiment shown in any one of FIG. 1 to FIG. 3 when the computer program is executed.的 Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here. The device embodiments described above are only schematic, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, may be located One place, or it can be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the objective of the solution of this embodiment. Those of ordinary skill in the art can understand and implement without creative labor. Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary universal hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above-mentioned technical solution essentially or part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk. , Optical discs, and the like, including a number of instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the methods described in various embodiments or certain parts of the embodiments. Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application, rather than limiting them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that it can still Modifications to the technical solutions described in the foregoing embodiments, or equivalent replacements of some of the technical features thereof; and these modifications or replacements do not depart the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
401‧‧‧採集終端401‧‧‧collection terminal
402、502‧‧‧認證伺服器402, 502‧‧‧ authentication server
501‧‧‧檢測終端501‧‧‧test terminal
601‧‧‧檢測模組601‧‧‧ Detection Module
602‧‧‧判斷模組602‧‧‧Judgment Module
603‧‧‧第一識別模組603‧‧‧The first identification module
604‧‧‧第二識別模組604‧‧‧Second Identification Module
801‧‧‧處理組件801‧‧‧Processing component
802‧‧‧記憶體802‧‧‧Memory
803‧‧‧採集組件803‧‧‧Acquisition component
為了更清楚地說明本申請實施例或現有技術中的技術方案,下面將對實施例或現有技術描述中所需要使用的附圖作一簡單地介紹,顯而易見地,下面描述中的附圖是本申請的一些實施例,對於本領域普通技術人員來講,在不付出創造性勞動的前提下,還可以根據這些附圖獲得其他的附圖。 圖1示出了本申請提供的一種資訊識別方法一個實施例的流程圖; 圖2示出了本申請提供的一種資訊識別方法又一個實施例的流程圖; 圖3示出了本申請提供的一種資訊識別方法又一個實施例的流程圖; 圖4示出了本申請提供的一種資訊識別系統一個實施例的結構示意圖; 圖5示出了本申請提供的一種資訊識別系統又一個實施例的結構示意圖; 圖6示出了本申請提供的一種資訊識別裝置一個實施例的結構示意圖; 圖7示出了本申請提供的一種資訊識別裝置又一個實施例的結構示意圖; 圖8示出了本申請提供的一種電子設備一個實施例的結構示意圖; 圖9示出了本申請提供的一種電子設備又一個實施例的結構示意圖。In order to explain the technical solutions in the embodiments of the present application or the prior art more clearly, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are Some embodiments of the application, for those of ordinary skill in the art, can obtain other drawings according to the drawings without paying creative labor. FIG. 1 shows a flowchart of an embodiment of an information recognition method provided by the present application; FIG. 2 shows a flowchart of another embodiment of an information recognition method provided by the present application; FIG. 3 shows a flowchart provided by the present application A flowchart of yet another embodiment of an information recognition method; FIG. 4 shows a schematic structural diagram of an embodiment of an information recognition system provided by the present application; FIG. 5 shows another embodiment of an information recognition system provided by the present application. Schematic diagram; FIG. 6 shows a structure diagram of an embodiment of an information recognition device provided by the present application; FIG. 7 shows a structure diagram of another embodiment of an information recognition device provided by the present application; FIG. 8 shows the present invention. A schematic structural diagram of an embodiment of an electronic device provided by the application; FIG. 9 shows a schematic structural diagram of another embodiment of an electronic device provided by the application.
Claims (17)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
??201710884606.X | 2017-09-26 | ||
CN201710884606.XA CN109558773B (en) | 2017-09-26 | 2017-09-26 | Information identification method and device and electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
TW201915830A true TW201915830A (en) | 2019-04-16 |
Family
ID=65863117
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW107119428A TW201915830A (en) | 2017-09-26 | 2018-06-06 | Information recognition method and apparatus, and electronic device |
Country Status (3)
Country | Link |
---|---|
CN (1) | CN109558773B (en) |
TW (1) | TW201915830A (en) |
WO (1) | WO2019062588A1 (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111275649A (en) * | 2020-02-03 | 2020-06-12 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
CN111401463B (en) * | 2020-03-25 | 2024-04-30 | 维沃移动通信有限公司 | Method for outputting detection result, electronic equipment and medium |
CN111582047A (en) * | 2020-04-15 | 2020-08-25 | 浙江大华技术股份有限公司 | Face recognition verification passing method and related device thereof |
CN111522795A (en) * | 2020-04-23 | 2020-08-11 | 北京互金新融科技有限公司 | Method and device for processing data |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2009142098A1 (en) * | 2008-04-23 | 2009-11-26 | 日本電気株式会社 | Image processing device, camera, image processing method, and program |
US8121358B2 (en) * | 2009-03-06 | 2012-02-21 | Cyberlink Corp. | Method of grouping images by face |
CN102254148A (en) * | 2011-04-18 | 2011-11-23 | 周曦 | Method for identifying human faces in real time under multi-person dynamic environment |
CN102880864A (en) * | 2012-04-28 | 2013-01-16 | 王浩 | Method for snap-shooting human face from streaming media file |
CN103491351A (en) * | 2013-09-29 | 2014-01-01 | 东南大学 | Intelligent video monitoring method for illegal buildings |
CN104581003A (en) * | 2013-10-12 | 2015-04-29 | 北京航天长峰科技工业集团有限公司 | Video rechecking positioning method |
US9524418B2 (en) * | 2014-06-05 | 2016-12-20 | Promethean Limited | Systems and methods for detecting, identifying and tracking objects and events over time |
CN104038742B (en) * | 2014-06-06 | 2017-12-01 | 上海卓悠网络科技有限公司 | A kind of door bell and button system based on face recognition technology |
CN105205482B (en) * | 2015-11-03 | 2018-10-26 | 北京英梅吉科技有限公司 | Fast face feature recognition and posture evaluation method |
CN106446816B (en) * | 2016-09-14 | 2019-12-27 | 北京旷视科技有限公司 | Face recognition method and device |
CN107105310B (en) * | 2017-05-05 | 2020-07-10 | 广州盈可视电子科技有限公司 | Human image replacing method and device in video live broadcast and recording and broadcasting system |
-
2017
- 2017-09-26 CN CN201710884606.XA patent/CN109558773B/en active Active
-
2018
- 2018-06-06 TW TW107119428A patent/TW201915830A/en unknown
- 2018-09-18 WO PCT/CN2018/106102 patent/WO2019062588A1/en active Application Filing
Also Published As
Publication number | Publication date |
---|---|
CN109558773A (en) | 2019-04-02 |
WO2019062588A1 (en) | 2019-04-04 |
CN109558773B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111191539B (en) | Certificate authenticity verification method and device, computer equipment and storage medium | |
TW201915830A (en) | Information recognition method and apparatus, and electronic device | |
WO2019033572A1 (en) | Method for detecting whether face is blocked, device and storage medium | |
US20170330028A1 (en) | Facial matching system | |
WO2015165365A1 (en) | Facial recognition method and system | |
CN111626371B (en) | Image classification method, device, equipment and readable storage medium | |
CN110866466B (en) | Face recognition method, device, storage medium and server | |
CN103914686A (en) | Face comparison authentication method and system based on identification photo and collected photo | |
CN110008909B (en) | Real-name system business real-time auditing system based on AI | |
CN103324912A (en) | Face recognition system and method for ATM | |
WO2020244071A1 (en) | Neural network-based gesture recognition method and apparatus, storage medium, and device | |
Tiwari et al. | A touch-less fingerphoto recognition system for mobile hand-held devices | |
CN108171138B (en) | Biological characteristic information acquisition method and device | |
US11281922B2 (en) | Face recognition system, method for establishing data of face recognition, and face recognizing method thereof | |
Bong et al. | Palm print verification system | |
Chawla et al. | A robust algorithm for iris segmentation and normalization using hough transform | |
CN114698399A (en) | Face recognition method and device and readable storage medium | |
JP2009129237A (en) | Image processing apparatus and its method | |
Ibrahim | Iris recognition using Haar wavelet transform | |
Shinde et al. | Fingerprint Recognition Based on Deep Learning Pre-Train with Our Best CNN Model for Person Identification | |
Tinuke Omolewa et al. | Framework for User Authentication at a Distance for Mobile Phones Using Contactless Hand-based Multimodal Biometric System. | |
Ashwini et al. | Evaluation of iris recognition system on multiple feature extraction algorithms and its combinations | |
Sehgal | Palm recognition using LBP and SVM | |
US20220343681A1 (en) | Evaluating method and system for face verification, and computer storage medium | |
Sree et al. | Dorsal Hand Vein Pattern Authentication by Hough Peaks |