TWI570635B - Identification method of image frame and electronic device performing the same, computer readable recording medium storing program - Google Patents

Identification method of image frame and electronic device performing the same, computer readable recording medium storing program Download PDF

Info

Publication number
TWI570635B
TWI570635B TW105107019A TW105107019A TWI570635B TW I570635 B TWI570635 B TW I570635B TW 105107019 A TW105107019 A TW 105107019A TW 105107019 A TW105107019 A TW 105107019A TW I570635 B TWI570635 B TW I570635B
Authority
TW
Taiwan
Prior art keywords
image
data
original
adjusted
electronic device
Prior art date
Application number
TW105107019A
Other languages
Chinese (zh)
Other versions
TW201732681A (en
Inventor
陳志和
李文彬
陳郁婷
Original Assignee
和碩聯合科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 和碩聯合科技股份有限公司 filed Critical 和碩聯合科技股份有限公司
Priority to TW105107019A priority Critical patent/TWI570635B/en
Priority to CN201610939729.4A priority patent/CN107169495B/en
Application granted granted Critical
Publication of TWI570635B publication Critical patent/TWI570635B/en
Publication of TW201732681A publication Critical patent/TW201732681A/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/56—Extraction of image or video features relating to colour
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/01—Conversion of standards, e.g. involving analogue television standards or digital television standards processed at pixel level

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Controls And Circuits For Display Device (AREA)

Description

圖像辨識方法及執行該方法之電子裝置、電腦可讀取記錄媒體Image recognition method and electronic device and computer readable recording medium for performing the same

本發明係關於一種圖像辨識方法，特別是一種應用在影像處理品質檢測中之圖像辨識方法。The invention relates to an image recognition method, in particular to an image recognition method applied in image processing quality detection.

數位視訊轉換器(Set-Top Box, STB)具有解碼數位訊號之功能，可將來自無線、有線、衛星或網路等數位訊號轉換為類比訊號。通常，此類產品出廠前，會經過嚴格的品質檢測程序，以檢測經該數位視訊轉換器轉換後之影像畫面之品質是否符合標準。The Set-Top Box (STB) has the function of decoding digital signals, which can convert digital signals from wireless, cable, satellite or network into analog signals. Usually, such products undergo a rigorous quality inspection procedure before shipment to detect whether the quality of the image after conversion by the digital video converter conforms to the standard.

動態影像是由多張連續圖像所組成的，影像測試時，測試系統會由該多張圖像中擷取其一來進行相似度比對。然而，由於測試系統係自多張圖像中隨機擷取，因此在要將擷取到的圖像與原始圖像進行相似度比對前，測試系統必須先辨識所擷取到的圖像是第幾張圖像。A motion picture is composed of a plurality of consecutive images. When the image is tested, the test system extracts one of the multiple images for similarity comparison. However, since the test system is randomly captured from multiple images, the test system must first recognize the captured image before comparing the captured image with the original image. The first few images.

現有一種的圖像辨識作法是在各張原始圖像上標記不同的序號字元，以在擷取到特定某張圖像時，透過光學字元辨識技術，取得圖像上的序號字元，之後再根據該序號字元判斷所擷取到的圖像為第幾張圖像。然而，當所擷取到的圖像相較於原始圖像有所放大或縮小時，字元字體會產生變形，此將造成字元辨識難度的增加。An existing image recognition method is to mark different serial number characters on each original image, so as to obtain a serial number character on the image through an optical character recognition technology when capturing a specific image. Then, according to the serial number character, it is judged that the captured image is the first image. However, when the captured image is enlarged or reduced compared to the original image, the font of the character will be distorted, which will increase the difficulty of character recognition.

本發明之主要目的係在提供一種圖像辨識方法及電腦可讀取記錄媒體。The main object of the present invention is to provide an image recognition method and a computer readable recording medium.

本發明之另一主要目的係在提供一種可執行上述圖像辨識方法之電子裝置。Another main object of the present invention is to provide an electronic device that can perform the above image recognition method.

為達成上述之目的，本發明之圖像辨識方法適用於一電子裝置，電子裝置電性連接一視訊轉換器，該視訊轉換器用以轉換一原始資料圖像為一播放資料圖像，其中原始資料圖像之預設位置上之像素包括有原始識別顏色資料。本發明之圖像辨識方法包括有以下步驟：擷取該播放資料圖像；調整該播放資料圖像之圖面邊長至與該原始資料圖像之圖面邊長實質上相等，以取得一調整後資料圖像，其中該調整後資料圖像，相應於原始資料圖像之該預設位置相同位置上之像素，包括有調整後識別顏色資料；將調整後識別顏色資料經二值化處理，以取得一辨識資料；以及，根據該辨識資料取得對應的原始資料圖像。In order to achieve the above object, the image recognition method of the present invention is applicable to an electronic device. The electronic device is electrically connected to a video converter, and the video converter is configured to convert an original data image into a play data image, wherein the original data The pixels at the preset position of the image include the original recognized color data. The image recognition method of the present invention comprises the steps of: capturing the play data image; and adjusting a side length of the play data image to be substantially equal to a length of a side of the original data image to obtain a The adjusted data image, wherein the adjusted data image corresponds to a pixel at the same position of the preset position of the original data image, including the adjusted color data after adjustment; and the adjusted color data is binarized after the adjustment , to obtain an identification data; and, according to the identification data, obtain a corresponding original data image.

此外，本發明揭示一種內儲程式之電腦可讀取記錄媒體，當電腦載入該程式並執行後，可完成上述之圖像辨識方法。In addition, the present invention discloses a computer readable recording medium with a built-in program. When the computer loads the program and executes it, the image recognition method described above can be completed.

為達成上述之另一目的，本發明之電子裝置可電性連接一視訊轉換器，該視訊轉換器用以轉換原始資料圖像為播放資料圖像其中該原始資料圖像之預設位置上之像素包括原始識別顏色資料。本發明之電子裝置包括有影像擷取裝置及處理器。影像擷取裝置用以擷取該播放資料圖像。處理器係與影像擷取裝置電性連接，處理器用以調整播放資料圖像之圖面邊長至與原始資料圖像之圖面邊長實質上相等，以取得一調整後資料圖像，其中該調整後資料圖像，相應於原始資料圖像之該預設位置相同位置上的像素，包括有調整後識別顏色資料；取得調整後識別顏色資料，處理器更用以將調整後識別顏色資料經二值化處理，以取得一辨識資料，並根據該辨識資料取得對應的原始資料圖像。To achieve the above other object, the electronic device of the present invention can be electrically connected to a video converter, and the video converter is configured to convert the original data image into a playback material image, wherein the pixel of the original data image is preset. Includes original identification color data. The electronic device of the present invention includes an image capturing device and a processor. The image capturing device is configured to capture the image of the playing material. The processor is electrically connected to the image capturing device, and the processor is configured to adjust the length of the image side of the playback data image to be substantially equal to the length of the image side of the original data image, to obtain an adjusted data image, wherein The adjusted data image corresponds to the pixel at the same position of the preset position of the original data image, including the adjusted color data after the adjustment; the adjusted color data is obtained after the adjustment, and the processor is further configured to identify the color data after adjustment The binarization process is performed to obtain an identification data, and the corresponding original data image is obtained according to the identification data.

為能讓 貴審查委員能更瞭解本發明之技術內容，特舉較佳具體實施例說明如下。In order to enable the reviewing committee to better understand the technical contents of the present invention, the preferred embodiments are described below.

以下請參考圖1關於本發明之電子裝置之使用環境示意圖，並請一併參考圖2至圖4，其中圖2係表示原始資料圖像之示意；圖3係表示不同的原始資料圖像複數預設位置上之像素的顏色資料之示意；圖4係表示辨識資料對照原始資料影像之示意。Please refer to FIG. 1 for a schematic diagram of the use environment of the electronic device of the present invention, and please refer to FIG. 2 to FIG. 4 together, wherein FIG. 2 is a schematic diagram showing an original material image; FIG. 3 is a diagram showing different original image data. The indication of the color data of the pixel at the preset position; FIG. 4 is a schematic representation of the identification data against the original data image.

如圖1所示，在本發明之一實施例中，本發明揭示之電子裝置1係可電性連接一視訊轉換器90，該視訊轉換器90係可與影像播放器(圖未示)電性連接，視訊轉換器90用以轉換由影像播放器輸入的複數原始資料圖像O，以對應產生複數播放資料圖像P。在本發明之具體實施例中，視訊轉換器90為數位視訊轉換盒(Set-Top Bo, STB)，但本發明並不以此為限。As shown in FIG. 1 , in an embodiment of the present invention, the electronic device 1 of the present invention is electrically connected to a video converter 90, and the video converter 90 can be electrically connected to a video player (not shown). The video converter 90 is configured to convert the plurality of original data images O input by the video player to generate a plurality of playback material images P. In a specific embodiment of the present invention, the video converter 90 is a digital video conversion box (Set-Top Bo, STB), but the invention is not limited thereto.

本發明之電子裝置1可用以測試視訊轉換器90執行圖像轉換之品質。測試時，會由影像播放器播放測試影片，以產生複數幅原始資料圖像O。如圖2所示，其係表示原始資料圖像O之一實施示意。每一幅原始資料圖像O皆是由複數像素T1~T3、P4~P20所構成，其中原始資料圖像O之複數預設位置上之像素T1、T2、T3各包括有原始識別顏色資料及位置資料，不同的原始資料圖像O，其像素T1、T2、T3的原始識別顏色資料之組合各有不同。舉例來說，以圖3所示為例，編號1之原始資料圖像O之像素T1、T2、T3的原始識別顏色資料分別為(0、0、0)、(0、0、0)及(255、255、255)，編號2之原始資料圖像O之像素T1、T2、T3的原始識別顏色資料分別為(0、0、0)、(255、255、255)及(0、0、0)，二者像素T1之原始識別顏色資料雖然相同，但像素T1、T2、T3的原始識別顏色資料之組合不會全部相同(因為二者的像素T2、T3之原始識別顏色資料不同)；再舉例言之，編號6之原始資料圖像O之像素T1、T2、T3的原始識別顏色資料分別為(255、255、255)、(255、255、255)及(0、0、0)，編號7之原始資料圖像O之像素T1、T2、T3的原始識別顏色資料分別為(255、255、255)、(255、255、255)及(255、255、255)，此處雖然兩者的像素T1、T2之原始識別顏色資料相同，但兩者的像素T3之原始識別顏色資料不同，故像素T1、T2、T3的原始識別顏色資料之組合為不相同。在本發明之具體實施例中，原始資料圖像O之像素T1、T2、T3所在位置係位於原始資料圖像O上側邊緣且由最左側開始沿著圖像寬度方向W連續排列(如圖2所示)，但本發明不以此為限，像素T1、T2、T3也可預設位於任意位置上。The electronic device 1 of the present invention can be used to test the quality of image conversion performed by the video converter 90. During the test, the test video is played by the video player to generate a plurality of original data images O. As shown in FIG. 2, it shows an implementation of one of the original material images O. Each of the original data images O is composed of a plurality of pixels T1~T3, P4~P20, wherein the pixels T1, T2, and T3 at a plurality of preset positions of the original data image O respectively include original identification color data and The location data, the different original image images O, and the combinations of the original recognized color data of the pixels T1, T2, and T3 are different. For example, taking the example shown in FIG. 3, the original recognized color data of the pixels T1, T2, and T3 of the original data image No. 1 of the number 1 are (0, 0, 0), (0, 0, 0), and (255, 255, 255), the original identification color data of the pixels T1, T2, and T3 of the original data image No. 2 of the number 2 are (0, 0, 0), (255, 255, 255), and (0, 0, respectively). 0), the original recognition color data of the two pixels T1 are the same, but the combination of the original recognition color data of the pixels T1, T2, T3 is not all the same (because the original recognition color data of the pixels T2 and T3 of the two are different) For example, the original identification color data of the pixels T1, T2, and T3 of the original data image No. 6 of number 6 are (255, 255, 255), (255, 255, 255), and (0, 0, 0, respectively). ), the original identification color data of the pixels T1, T2, and T3 of the original data image No. 7 of No. 7 are (255, 255, 255), (255, 255, 255), and (255, 255, 255), respectively. Although the original identification color data of the pixels T1 and T2 of the two are the same, the original identification color data of the pixels T3 of the two are different, so the combination of the original recognized color data of the pixels T1, T2, and T3 is not the same. . In a specific embodiment of the present invention, the positions of the pixels T1, T2, and T3 of the original material image O are located on the upper side edge of the original material image O and are successively arranged along the image width direction W from the leftmost side (see FIG. 2). Shown), but the invention is not limited thereto, and the pixels T1, T2, T3 can also be preset to be located at any position.

如圖1所示，在本發明之一實施例中，本發明之電子裝置1包括有影像擷取裝置10、記憶體20以及處理器30。As shown in FIG. 1 , in an embodiment of the present invention, an electronic device 1 of the present invention includes an image capturing device 10 , a memory 20 , and a processor 30 .

在本發明之一實施例中，影像擷取裝置10，例如可為影像擷取卡，係用以擷取播放資料圖像P。In an embodiment of the present invention, the image capturing device 10 can be, for example, an image capturing card for capturing a playback material image P.

在本發明之一實施例中，記憶體20中儲存有軟體程式S及資料庫D，其中資料庫D記錄如圖4所示之對照表，此對照表可提供處理器30根據取得的辨識資料查找出相對應的原始資料圖像O。關於辨識資料之取得以下會有詳細之說明，在此暫不予贅述。In an embodiment of the present invention, the software 20 stores a software program S and a database D, wherein the database D records a comparison table as shown in FIG. 4, and the comparison table can provide the identification data obtained by the processor 30 according to the data. Find the corresponding original data image O. The following is a detailed description of the identification data, and will not be repeated here.

在本發明之一實施例中，處理器30，例如可為中央處理單元(Central Processing Unit, CPU)，係與影像擷取裝置10及記憶體20電性連接。處理器30可將軟體程式S載入後執行，以實現本發明以下將說明的圖像辨識方法。處理器30載入軟體程式S後執行之功能，於以下說明本發明之圖像辨識方法時，將一併說明之，在此暫不予贅述。In one embodiment of the present invention, the processor 30 can be, for example, a central processing unit (CPU), and is electrically connected to the image capturing device 10 and the memory 20. The processor 30 can execute the loading of the software program S to implement the image recognition method which will be described below. The function performed by the processor 30 after loading the software program S will be described below in conjunction with the image recognition method of the present invention, and will not be described herein.

接著，請參考圖5關於本發明之圖像辨識方法之步驟流程圖，並一併參考圖1-4及圖6-8，其中圖6係表示原始資料圖像經視訊轉換器轉換後被放大之示意；圖7係表示調整後資料圖像之示意；圖8係表示調整後資料圖像預設位置上之像素的顏色資料產生之示意。需注意的是，以下雖是圖1中所示之電子裝置1為例，說明本發明所揭露之圖像辨識方法，惟本發明之圖像辨識方法並不以適用於該電子裝置1為限。Next, please refer to FIG. 5 for a flowchart of the steps of the image recognition method of the present invention, and refer to FIG. 1-4 and FIG. 6-8 together, wherein FIG. 6 shows that the original data image is enlarged after being converted by the video converter. FIG. 7 is a schematic diagram showing an adjusted data image; FIG. 8 is a schematic diagram showing the generation of color data of pixels at a preset position of the adjusted data image. It should be noted that the following is an example of the electronic device 1 shown in FIG. 1 , which illustrates the image recognition method disclosed in the present invention. However, the image recognition method of the present invention is not applicable to the electronic device 1 . .

如圖5所示，首先，執行步驟S1：擷取播放資料圖像。As shown in FIG. 5, first, step S1 is performed: capturing a play material image.

本發明之圖像辨識方法可辨識每一幅播放資料影像P，並依辨識結果找尋出相對應之圖像來執行相似度比對，藉以檢測視訊轉換器影像轉換之品質。為此，方法執行的第一步，即須就由視訊轉換器90轉換產生的複數播放資料圖像P中擷取其中一播放資料圖像P，以進行後續的圖像檢測動作。故在步驟S1中，電子裝置90之處理器30首先會控制影像擷取裝置10擷取一播放資料圖像P。The image recognition method of the present invention can identify each play data image P, and find a corresponding image according to the identification result to perform similarity comparison, thereby detecting the quality of the video converter image conversion. To this end, the first step of the method execution is to retrieve one of the playback material images P from the plurality of playback material images P converted by the video converter 90 for subsequent image detection operations. Therefore, in step S1, the processor 30 of the electronic device 90 first controls the image capturing device 10 to capture a play data image P.

接著，執行步驟S2：調整播放資料圖像之圖面寬度至與原始資料圖像之圖面寬度相等，以取得一調整後資料圖像。Then, step S2 is performed: adjusting the width of the image of the playback material image to be equal to the width of the image of the original data image to obtain an adjusted data image.

由於經由視訊轉換器90轉換後之圖像尺寸可能會產生變化，故在前揭步驟中所擷取到的播放資料圖像P之尺寸可能會較對應的原始資料圖像O大或小(亦即圖像被放大或被縮小)，導致播放資料圖像P相應於原始資料圖像O之複數預設位置相同位置上(即像素T1、T2、T3所在位置)的像素之顏色資料，會與像素T1、T2、T3之原始識別顏色資料有所不同。為求使播放資料圖像P和原始資料圖像O對應相同位置上的像素之顏色資料可以相同或接近一致，在步驟S2中，電子裝置1之處理器30會調整播放資料圖像P之圖面寬度至與原始資料圖像O之圖面寬度相等，以取得一調整後資料圖像J(如圖7所示)。Since the size of the image converted by the video converter 90 may change, the size of the playback material image P captured in the preceding step may be larger or smaller than the corresponding original image image O (also That is, the image is enlarged or reduced, causing the playback material image P to correspond to the color data of the pixels at the same position of the plurality of preset positions of the original data image O (ie, the positions where the pixels T1, T2, and T3 are located), and The original recognized color data of the pixels T1, T2, and T3 are different. In order to make the color data of the pixels corresponding to the same position in the playback material image P and the original data image O can be the same or nearly identical, in step S2, the processor 30 of the electronic device 1 adjusts the image of the playback material image P. The width of the face is equal to the width of the image of the original data image O to obtain an adjusted data image J (as shown in FIG. 7).

以圖6所示為例，假設原始資料圖像O之圖面寬度為5個單位長度，當其經由視訊轉換器90轉換後所產生的播放資料圖像P的圖面寬度為8單位長度時，為了將播放資料圖像P之圖面寬度調整到與原始資料圖像O的圖面寬度相等，電子裝置1之處理器30會將播放資料圖像P的圖面寬度乘以原始資料圖像O之圖面寬度與播放資料圖像P之圖面寬度之比值(本例中為5/8)，即： W j＝W p*W o/W p其中W j表示調整後資料圖像J之圖面寬度，W p為播放資料圖像P的圖面寬度，W o為原始資料圖像O之圖面寬度。 Taking the example shown in FIG. 6 as an example, it is assumed that the plane width of the original material image O is 5 unit lengths, and when the plane width of the playback material image P generated by the conversion by the video converter 90 is 8 unit length In order to adjust the plane width of the playback material image P to be equal to the plane width of the original material image O, the processor 30 of the electronic device 1 multiplies the plane width of the playback material image P by the original data image. The ratio of the width of the plane of O to the width of the plane of the playback material image P (5/8 in this example), ie: W j = W p *W o /W p where W j represents the adjusted image image J The width of the drawing, W p is the width of the drawing of the playback material image P, and W o is the width of the drawing of the original data image O.

進一步言之，於上述例子中，調整後資料圖像J之圖面寬度也可說是藉由將播放資料圖像P之圖面寬度先放大5倍後，再縮小8倍而取得。此處放大及縮小倍數取得之一具體實施方式，但不以為限的是，可先計算取得原始資料圖像O之圖面寬度與播放資料圖像P之圖面寬度的最小公倍數C(本例中即為40)，接著將最小公倍數C除以播放資料圖像P之圖面寬度與原始資料圖像O之圖面寬度，以分別得到X(本例中為5)及Y(本例中為8)。而調整後資料圖像J之圖面寬度(等同原始圖像之圖面寬度)即可藉由播放資料圖像之圖面寬度放大X倍後，再縮小Y倍取得。Further, in the above example, the width of the image of the adjusted data image J can be obtained by first magnifying the width of the image of the playback material image P by a factor of five and then reducing it by eight times. Herein, one embodiment of the enlargement and reduction of the multiple is obtained, but it is not limited to, the least common multiple C of the width of the image of the original data image O and the width of the image of the playback data image P can be calculated first (in this example). The middle is 40), and then the least common multiple C is divided by the width of the image of the playback material image P and the width of the original image image O to obtain X (in this example, 5) and Y (in this example) For 8). The width of the image of the adjusted image image J (equivalent to the width of the original image) can be obtained by zooming in on the width of the image of the data image by X times and then reducing it by Y times.

調整後，取得的調整後資料圖像J中，對應於原始資料圖像O之複數預設位置相同位置上(即像素T1、T2、T3所在位置)之像素T1’、T2’、T1’各包括有一調整後識別顏色資料，各調整後識別顏色資料會與原始資料圖像O之像素T1、T2、T3的原始識別顏色資料實質上相同或大致接近，三者資料之計算示意可參考圖8。如圖8所示，播放資料圖像P之圖面寬度放大5倍(即乘以5)時會與原始資料圖像O圖面寬度放大8倍(即乘以8)時等長，假設擷取到的播放資料圖像P上側邊緣且由最左側開始沿著圖像寬度W方向連續排列的像素如圖8標示之擷取圖所示，將其放大5倍後產生之圖像相同位置上的像素排列即會如圖8標示之放大擷取圖所示。此時，再將放大5倍的播放資料圖像P縮小8倍(即除以8)，所產生的調整後資料圖像J上側邊緣且由最左側之像素T1’之調整後識別顏色資料即會等於(X1*5+X2*3)/8，上側邊緣且由最左側往右數來第2個像素T2’ 之調整後識別顏色資料等於(X2*2+X3*5+X4*1)/8、上側邊緣且由最左側往右數來第3個像素T3’的調整後識別顏色資料等於(X4*4+X5*4)/8。After the adjustment, the obtained adjusted data image J corresponds to the pixels T1', T2', T1' corresponding to the plurality of preset positions of the original data image O (ie, the positions where the pixels T1, T2, and T3 are located). Including an adjusted color data after adjustment, each adjusted color data is substantially the same as or substantially close to the original recognized color data of the pixels T1, T2, and T3 of the original data image O, and the calculation of the three data can be referred to FIG. . As shown in Fig. 8, when the width of the image of the playback material image P is enlarged by 5 times (i.e., multiplied by 5), it is equal to the width of the original image image O by 8 times (i.e., multiplied by 8), which is assumed to be 撷. The pixels on the upper edge of the playback material image P and successively arranged along the image width W direction from the leftmost side are as shown in the captured image of FIG. 8 , and are magnified 5 times to generate the image at the same position. The pixel arrangement will be as shown in the enlarged view of Figure 8. At this time, the playback material image P enlarged by 5 times is further reduced by 8 times (that is, divided by 8), and the generated upper side edge of the adjusted data image J and the adjusted color data by the leftmost pixel T1' are Will be equal to (X1*5+X2*3)/8, the upper side edge and the leftmost to the right number of the second pixel T2' after the adjusted color data is equal to (X2*2+X3*5+X4*1) /8, the upper side edge and the adjusted color data of the third pixel T3' from the leftmost to the right is equal to (X4*4+X5*4)/8.

此處須注意的是，由於本實施例中，原始資料圖像O之像素T1、T2、T3所在位置是預設在原始資料圖像O上側邊緣且由最左側開始沿著圖像寬度方向W連續排列(如圖2所示)，因此，圖像在放大或縮小時，同一位置上的顏色資料僅會受到圖面寬度變化而影響(如圖8所示)，故在此只做圖面寬度之調整即可，但本發明不以此為限；倘若像素T1、T2、T3所在位置是預設在原始資料圖像O左或右兩側之邊緣且由最上側(或最下側)開始沿著圖像高度方向H連續排列的話，此時可僅就圖面高度做調整即可，也就是說，調整後資料圖像J是透過調整原始資料圖像O之圖面邊長而取得，而此處所謂「圖面邊長」可以是圖面寬度，也可以是圖面高度。又如果像素T1、T2、T3之位置不是預設位在圖像邊緣時，且圖像之圖面寬度及高度皆被放大或縮小時，即須就圖面寬度及高度皆進行調整。由於不論係圖面寬度或/及高度之調整(包含放大或縮小)，其調整後各位置像素之顏色資料計算產生之原理皆同於前揭之說明，且其為所屬領域具通常知識者所熟悉，故在此予以省略說明。此外，應可理解的是，如果播放資料圖像P之尺寸同於原始資料圖像O之尺寸，則此處的圖面寬度或高度之調整即為播放資料圖像P之圖面寬度或高度乘於1(即調整後未被放大或縮小)。It should be noted here that, in this embodiment, the positions of the pixels T1, T2, and T3 of the original material image O are preset on the upper side edge of the original material image O and start from the leftmost side along the image width direction W. Continuously arranged (as shown in Figure 2), therefore, when the image is enlarged or reduced, the color data at the same position will only be affected by the change of the width of the surface (as shown in Figure 8), so only the surface is made here. The adjustment of the width is sufficient, but the invention is not limited thereto; if the positions of the pixels T1, T2, and T3 are preset on the left or right sides of the original material image O and are from the uppermost side (or the lowermost side) When starting to be continuously arranged along the height direction H of the image, it is only necessary to adjust the height of the surface at this time, that is, the adjusted data image J is obtained by adjusting the side length of the original image image O. Here, the "side length of the drawing" may be the width of the drawing or the height of the drawing. Moreover, if the positions of the pixels T1, T2, and T3 are not preset at the edge of the image, and the width and height of the image are enlarged or reduced, the width and height of the image must be adjusted. Since the adjustment of the width or/and height of the image plane (including enlargement or reduction), the principle of calculating the color data of each pixel after adjustment is the same as the description of the foregoing, and it is a common knowledge in the field. I am familiar with it, so the description is omitted here. In addition, it should be understood that if the size of the playback material image P is the same as the size of the original data image O, the adjustment of the width or height of the image surface herein is the width or height of the image of the playback material image P. Multiply by 1 (ie, it is not enlarged or reduced after adjustment).

執行步驟S3：將各調整後識別顏色資料經二值化處理，以取得一辨識資料。Step S3 is performed: binarizing the adjusted color data to obtain an identification data.

如圖7所示，在完成步驟S2後，接著，電子裝置1之處理器30會將調整後資料圖像J中，對應原始資料圖像O之像素T1、T2、T3所在相同位置上的像素T1’、T2’、T1’的調整後識別顏色資料經二值化處理，以取得一辨識資料。As shown in FIG. 7, after the step S2 is completed, the processor 30 of the electronic device 1 will correspond to the pixel at the same position of the pixels T1, T2, and T3 of the original material image O in the adjusted data image J. The adjusted color data of T1', T2', T1' is binarized to obtain an identification data.

由於視訊轉換器90轉換後之圖像的各個像素之顏色資料，有可能會因為影像處理品質之優劣而與原先輸入之圖像有所不同，例如原始圖像某一位置之像素的顏色資料本為(255、255、255)，但其經視訊轉換器90轉換後所產生之圖像，同一位置上之顏色資料可能會變為(235,220,245)。因此，為避免誤判，本發明之圖像辨識方法會進一步將調整後識別顏色資料進行二值化處理。在本實施例中，本發明二值化處理所預設的閾值為80，也就是說，若顏色資料之數值大於80，即設為1，反之，即設為0 (程式碼：If value ＞ 80 then set_H, else set_L)。以上述例子顏色資料為(235,220,245)為例，經本發明所述之二值化處理後即會取得資料(1,1,1)。再舉例言之，若自預設位置上取得的顏色資料為(10,15,30)，則經二值化處理後即會取得資料(0,0,0)。Due to the color data of each pixel of the image converted by the video converter 90, it may be different from the originally input image because of the quality of the image processing quality, for example, the color data of the pixel at a certain position of the original image. For (255, 255, 255), but the image produced by the conversion of the video converter 90, the color data at the same position may become (235, 220, 245). Therefore, in order to avoid misjudgment, the image recognition method of the present invention further performs binarization processing on the adjusted color data after adjustment. In this embodiment, the threshold value preset by the binarization processing of the present invention is 80, that is, if the value of the color data is greater than 80, it is set to 1, otherwise, it is set to 0 (code: If value > 80 then set_H, else set_L). Taking the color data of the above example as (235, 220, 245) as an example, the data (1, 1, 1) will be obtained after the binarization process described in the present invention. For example, if the color data obtained from the preset position is (10, 15, 30), the data (0, 0, 0) is obtained after the binarization processing.

由於本發明一開始是以原始資料圖像O之像素T1、T2、T3的原始識別顏色資料作為圖像辨識之判斷，而這些像素T1、T2、T3之原始識別顏色資料會被事先設定，且預設的數值皆會與二值化處理所設定的閾值相差甚鉅，例如圖3所示，編號1之原始資料圖像O的像素T1之原始識別顏色資料為(0、0、0)、像素T3之原始識別顏色資料(255、255、255)等，因此，即便播放資料圖像P之各個像素的顏色資料會與原始資料圖像O之像素的顏色資料有所落差，但變化皆不會跨越閾值，亦即數值0變化不會超過80，而數值255變化不會到低於80(因為此處閾值的設定會經由多次測試視訊轉換器90轉換的結果而決定)。從而，自調整後資料圖像J之像素T1’、T2’、T3’中取得的調整後識別顏色資料，其經二值化處理後所取得辨識資料內容，會與原始資料圖像O的像素T1、T2、T3之原始識別顏色資料經二值化處理後之資料內容相同。Since the present invention initially determines the original recognized color data of the pixels T1, T2, and T3 of the original data image O as the image recognition, the original recognized color data of the pixels T1, T2, and T3 are set in advance, and The preset value will be quite different from the threshold set by the binarization process. For example, as shown in FIG. 3, the original identification color data of the pixel T1 of the original data image O of number 1 is (0, 0, 0), The original color data (255, 255, 255) of the pixel T3 is recognized. Therefore, even if the color data of each pixel of the playback material image P is different from the color data of the pixel of the original data image O, the change is not The threshold will be crossed, that is, the value 0 will not change by more than 80, and the value 255 will not change below 80 (because the threshold setting here is determined by the result of multiple tests of the video converter 90 conversion). Therefore, the adjusted color data obtained from the pixels T1', T2', and T3' of the adjusted data image J, after the binarization processing, obtains the identification data content, and the pixel of the original data image O The original identification color data of T1, T2, and T3 is the same as the data content after the binarization processing.

執行步驟S4：根據辨識資料取得相應的原始資料圖像。Step S4 is performed: obtaining a corresponding original data image according to the identification data.

在依前揭說明取得辨識資料後，電子裝置1之處理器30即可根據辨識資料以及如圖4所示之對照表，查找出相應的原始資料圖像O。舉例而言，以圖3所示為例，假設原始資料圖像O之像素T1、T2、T3的原始識別顏色資料分別為(0、0、0)、(255、255、255)及(0、0、0)，而其經由視訊轉換器90轉換後產生的播放資料圖像P經圖面寬度調整後，所產生的調整後資料圖像J之像素T1’、T2’、T1’之調整後識別顏色資料假設分別為(10,15,30)、(250、235、240)及(10、35、20)，經二值化處理後取得的資料分別為(0,0,0)、(1,1,1)、(0,0,0)，此時處理器30會將(0,0,0)視作0、(1,1,1)視作1，則T1’、T2’、T1’依序為010，即代表編號2之原始資料圖像O(參照圖4所示)，此時處理器30可依據此辨識資料取得編號2之原始資料圖像O。再舉例言之，假設原始資料圖像O之像素T1、T2、T3的原始識別顏色資料分別為(255、255、255)、(255、255、255)及(0、0、0)，其經由視訊轉換器90轉換後產生的播放資料圖像P經圖面寬度調整後，所產生的調整後資料圖像J之像素T1’、T2’、T1’之調整後識別顏色資料假設分別為(230,245,250)、(250、235、240)及(10、35、20)，經二值化處理後取得的資料分別為(1,1,1)、(1,1,1)、(0,0,0)，同前述，此處會將(0,0,0)視作0、(1,1,1)視作1，則T1’、T2’、T1’依序為110，即代表編號6之原始資料圖像O(參照圖4所示)，此時處理器30即可依據辨識資料取得編號6之原始資料圖像O。在本發明之一實施例中，前揭根據辨識資料以取得對應的原始資料圖像，可透過比對該辨識資料與該原始識別顏色資料經二值化處理後所對應的資料而實現，但本發明不以此為限。舉例來說，當處理器30取得辨識資料(1,1,1)、(1,1,1)、(0,0,0)後，其會將該辨識資料與各原始資料圖像O之原始識別顏色資料經二值化處理後產生之資料逐一比對，並在比對出編號6之原始資料圖像O的原始識別顏色資料經二值化處理後的資料與該辨識資料(1,1,1)、(1,1,1)、(0,0,0)相符時，即取得編號6之原始資料圖像O作為比對用之資料圖像。After obtaining the identification data according to the foregoing description, the processor 30 of the electronic device 1 can find the corresponding original data image O according to the identification data and the comparison table shown in FIG. 4 . For example, taking the example shown in FIG. 3 as an example, it is assumed that the original recognized color data of the pixels T1, T2, and T3 of the original data image O are (0, 0, 0), (255, 255, 255), and (0, respectively). , 0, 0), and the playback material image P generated after the conversion by the video converter 90 is adjusted by the width of the image, and the adjusted adjustment of the pixels T1', T2', T1' of the generated data image J The post-identification color data are assumed to be (10, 15, 30), (250, 235, 240) and (10, 35, 20), respectively. The data obtained after binarization are (0, 0, 0), (1,1,1), (0,0,0), at this time processor 30 will treat (0,0,0) as 0, (1,1,1) as 1, then T1', T2 ', T1' is sequentially 010, that is, the original data image O (refer to FIG. 4) representing the number 2, at which time the processor 30 can obtain the original data image O of the number 2 according to the identification data. For example, it is assumed that the original recognized color data of the pixels T1, T2, and T3 of the original data image O are (255, 255, 255), (255, 255, 255), and (0, 0, 0), respectively. After the playback material image P generated by the conversion by the video converter 90 is adjusted by the picture width, the adjusted color data of the pixels T1', T2', and T1' of the adjusted data image J are assumed to be ( 230, 245, 250), (250, 235, 240) and (10, 35, 20). The data obtained after binarization are (1,1,1), (1,1,1), (0,0). , 0), as before, here (0,0,0) is treated as 0, (1,1,1) is treated as 1, then T1', T2', T1' are sequentially 110, which means the number The original data image O of 6 (shown in FIG. 4), at this time, the processor 30 can obtain the original data image O of the number 6 based on the identification data. In an embodiment of the present invention, the method for obtaining the corresponding original data according to the identification data may be implemented by comparing the data corresponding to the identification data and the original identification color data by binarization processing, but The invention is not limited thereto. For example, when the processor 30 obtains the identification data (1, 1, 1), (1, 1, 1), (0, 0, 0), it will associate the identification data with each original data image O. The data generated by the binarization processing of the original identification color data are compared one by one, and the data of the original identification color data of the original data image O of the number 6 is binarized and the identification data is compared (1, When 1,1), (1,1,1), (0,0,0) match, the original data image O of the number 6 is obtained as the data image for comparison.

最後，執行步驟S5：比對播放資料圖像與相應的原始資料圖像之相似度是否小於誤差範圍。Finally, step S5 is performed: whether the similarity between the comparison play image image and the corresponding original data image is smaller than the error range.

在取得相應的原始資料圖像後，電子裝置1之處理器30即會將原先擷取到的播放資料圖像P與執行前揭步驟而取得的原始資料圖像進行相似度比對，並判斷相似度差異是否小於誤差範圍。若是，則判斷視訊轉換器90影像轉換之品質通過測試，反之，若超過誤差範圍，則判該斷視訊轉換器90影像轉換之品質未通過測試。由於圖像相似度比對之技術為習用技術，其技術原理及內容散見在許多專利及技術文獻中，已為所屬領域具通常知識者所熟知，且本發明亦不限以特定方式實施，故在此就其細節即不多加贅述。After obtaining the corresponding original data image, the processor 30 of the electronic device 1 compares the original captured image data P with the original data image obtained by performing the pre-extracting step, and determines Whether the similarity difference is smaller than the error range. If so, it is judged that the quality of the image conversion of the video converter 90 passes the test. On the other hand, if the error range is exceeded, it is judged that the quality of the image conversion of the video converter 90 has not passed the test. Since the technique of image similarity comparison is a conventional technique, its technical principle and content are scattered in many patents and technical documents, and are well known to those skilled in the art, and the present invention is not limited to implementation in a specific manner. The details are not mentioned here.

在一些實施例中，上述所揭示之圖像辨識方法可實作為一電腦程式。所實作電腦程式可儲存於一電腦可讀取記錄媒體中，而使電腦讀取此記錄媒體後執行所揭露之圖像辨識方法。電腦可讀取記錄媒體可為唯讀記憶體、快閃記憶體、軟碟、硬碟、光碟、隨身碟、磁帶、可由網路存取之資料庫或熟習此技藝者可輕易思及具有相同功能之電腦可讀取紀錄媒體。In some embodiments, the image recognition method disclosed above can be implemented as a computer program. The implemented computer program can be stored in a computer readable recording medium, and the computer can execute the disclosed image recognition method after reading the recording medium. The computer readable recording medium can be read-only memory, flash memory, floppy disk, hard disk, optical disk, flash drive, tape, network accessible database or familiar with the art. The function of the computer can read the recording media.

藉由前揭說明可知，本發明揭示之圖像辨識方法是以圖像上預設位置之像素的顏色資料作為辨識用之資訊，透過被擷取圖像尺寸之調整，且將調整後圖像中與該預設位置相同位置之像素的顏色資料二值化處理，可使擷取到的圖像即便相較於原始圖像有所放大或縮小，或者顏色些許失真，也依然可依據調整後圖像之顏色資訊正確地找出相對應用以比對之圖像。As can be seen from the foregoing description, the image recognition method disclosed in the present invention uses the color data of the pixel at the preset position on the image as the information for identification, through the adjustment of the captured image size, and the adjusted image. The binarization of the color data of the pixel in the same position as the preset position enables the captured image to be enlarged or reduced compared to the original image, or the color is slightly distorted, and can still be adjusted according to the adjustment The color information of the image correctly finds the image relative to the application.

綜上所陳，本發明無論就目的、手段及功效，在在均顯示其迥異於習知技術之特徵，懇請  貴審查委員明察，早日賜准專利，俾嘉惠社會，實感德便。惟應注意的是，上述諸多實施例僅係為了便於說明而舉例而已，本發明所主張之權利範圍自應以申請專利範圍所述為準，而非僅限於上述實施例。To sum up, the present invention, regardless of its purpose, means and efficacy, shows its distinctive features of the prior art. You are requested to review the examination and express the patent as soon as possible. It should be noted that the various embodiments described above are merely illustrative for ease of explanation, and the scope of the invention is intended to be limited by the scope of the claims.

1‧‧‧電子裝置
10‧‧‧影像擷取裝置
20‧‧‧記憶體
S‧‧‧軟體程式
D‧‧‧資料庫
30‧‧‧處理器
90‧‧‧視訊轉換器
O‧‧‧原始資料圖像
P‧‧‧播放資料圖像
J‧‧‧調整後資料圖像
T1~T3、P4~P20‧‧‧原始資料圖像之像素
T1’~ T1’、P4’~P20’‧‧‧調整後資料圖像之像素1‧‧‧Electronic device
10‧‧‧Image capture device
20‧‧‧ memory
S‧‧‧ software program
D‧‧‧Database
30‧‧‧ Processor
90‧‧‧Video Converter
O‧‧‧ original image
P‧‧‧Playing material images
J‧‧‧Adjusted data image
P1~T3, P4~P20‧‧‧ pixel of original image
T1'~T1', P4'~P20'‧‧‧ pixels of the adjusted data image

圖1係本發明之電子裝置之使用環境示意圖。 圖2係表示原始資料圖像之示意。 圖3係表示不同的原始資料圖像複數預設位置上之像素的顏色資料之示意。 圖4係表示辨識資料對照原始資料影像之示意。 圖5係本發明之圖像辨識方法之步驟流程圖。 圖6係表示原始資料圖像經視訊轉換器轉換後被放大之示意。 圖7係表示調整後資料圖像之示意。 圖8係表示調整後資料圖像預設位置上之像素的顏色資料產生之示意。1 is a schematic view showing the use environment of the electronic device of the present invention. Figure 2 is a schematic representation of an original material image. FIG. 3 is a schematic diagram showing color data of pixels in a plurality of preset positions of different original material images. Figure 4 is a schematic representation of the identification data against the original data. Figure 5 is a flow chart showing the steps of the image recognition method of the present invention. Figure 6 is a diagram showing the original material image being enlarged after being converted by the video converter. Fig. 7 is a view showing an image of the adjusted data. FIG. 8 is a schematic diagram showing the generation of color data of pixels on the adjusted position of the adjusted data image.

1‧‧‧電子裝置 1‧‧‧Electronic device

10‧‧‧影像擷取裝置 10‧‧‧Image capture device

20‧‧‧記憶體 20‧‧‧ memory

S‧‧‧軟體程式 S‧‧‧ software program

D‧‧‧資料庫 D‧‧‧Database

30‧‧‧處理器 30‧‧‧ Processor

90‧‧‧視訊轉換器 90‧‧‧Video Converter

O‧‧‧原始資料圖像 O‧‧‧ original image

P‧‧‧播放資料圖像 P‧‧‧Playing material images

Claims (17)

一種圖像辨識方法，適用於一電子裝置，該電子裝置電性連接一視訊轉換器，該視訊轉換器用以轉換一原始資料圖像為一播放資料圖像，其中該原始資料圖像之一預設位置上之像素包括一原始識別顏色資料，該圖像辨識方法包括以下步驟： 擷取該播放資料圖像； 調整該播放資料圖像之圖面邊長至與該原始資料圖像之圖面邊長實質上相等，以取得一調整後資料圖像，其中該調整後資料圖像相應於該原始資料圖像之該預設位置相同位置上之像素包括一調整後識別顏色資料； 將該調整後識別顏色資料經二值化處理，以取得一辨識資料；以及 根據該辨識資料取得對應的該原始資料圖像。An image recognition method is applicable to an electronic device, the electronic device is electrically connected to a video converter, and the video converter is configured to convert an original data image into a play data image, wherein the original data image is pre- The pixel in the position includes an original identification color data, and the image recognition method comprises the following steps: capturing the playback material image; adjusting the length of the image side of the playback data image to the surface of the original data image The side lengths are substantially equal to obtain an adjusted data image, wherein the adjusted data image corresponds to the preset position of the original data image, and the pixel at the same position includes an adjusted color data; The post-identification color data is binarized to obtain an identification data; and the corresponding original material image is obtained according to the identification data. 如申請專利範圍第1項所述之圖像辨識方法，其中該調整後資料圖像之圖面邊長係以該播放資料圖像之圖面邊長乘以該原始資料圖像之圖面邊長與該播放資料圖像之圖面邊長之比值後取得。The image recognition method according to claim 1, wherein the adjusted side length of the data image is multiplied by the side length of the image of the play data image by the side of the original image image Obtained after the ratio of the length of the side of the image of the playback material image. 如申請專利範圍第1項所述之圖像辨識方法，其中調整該播放資料圖像之圖面寬度的步驟包括： 取得該原始資料圖像之圖面邊長與該播放資料圖像之圖面邊長的一最小公倍數； 該最小公倍數除以該播放資料圖像之圖面邊長得到X； 該最小公倍數除以該原始資料圖像之圖面邊長得到Y；以及 該播放資料圖像之圖面邊長放大X倍再縮小Y倍，而得到該調整後資料圖像之圖面邊長。The image recognition method of claim 1, wherein the step of adjusting a picture width of the play data image comprises: obtaining a picture side length of the original data image and a picture of the play data image a least common multiple of the side length; the least common multiple divided by the side length of the playback material image to obtain X; the least common multiple divided by the side length of the original data image to obtain Y; and the playback material image The side length of the drawing is enlarged by X times and then reduced by Y times, and the side length of the adjusted data image is obtained. 如申請專利範圍第1項所述之圖像辨識方法，其中該調整該播放資料圖像之圖面邊長至與該原始資料圖像之圖面邊長實質上相等的步驟，係調整該播放資料圖像之圖面寬度或高度至與該原始資料圖像之圖面寬度或高度實質上相等。The image recognition method of claim 1, wherein the step of adjusting the side of the image of the play data to be substantially equal to the length of the side of the original image is to adjust the play. The width or height of the image of the data image is substantially equal to the width or height of the image of the original image. 如申請專利範圍第4項所述之圖像辨識方法，其中該預設位置為複數，且當該複數預設位置位在該原始資料圖像之一側邊緣且沿著該原始資料圖像之圖像寬度方向連續排列時，該調整該播放資料圖像之圖面寬度至與該原始資料圖像之圖面寬度實質上相等。The image recognition method of claim 4, wherein the preset position is a complex number, and when the plurality of preset positions are located at one side edge of the original material image and along the original material image When the image width direction is continuously arranged, the width of the picture of the play data image is adjusted to be substantially equal to the picture width of the original data image. 如申請專利範圍第4項所述之圖像辨識方法，其中當該預設位置為複數，且該複數預設位置位在該原始資料圖像之一側邊緣且沿著該原始資料圖像之圖像高度方向連續排列時，調整該播放資料圖像之圖面高度至與該原始資料圖像之圖面高度實質上相等。The image recognition method of claim 4, wherein the preset position is a plural number, and the plurality of preset positions are located at one side edge of the original material image and along the original material image. When the height direction of the image is continuously arranged, the height of the surface of the play data image is adjusted to be substantially equal to the height of the image of the original data image. 如申請專利範圍第1項所述之圖像辨識方法，其中將各該調整後識別顏色資料經二值化處理，係將各該調整後識別顏色資料中數值大於一閾值之調整後識別顏色資料定義為1，而將各該調整後識別顏色資料數值小於或等於該閾值之調整後識別顏色資料定義為0，該設定閾值係根據該視訊轉換器解碼影像能力而設定。The image recognition method of claim 1, wherein each of the adjusted color data is binarized, and the adjusted color data is greater than a threshold value in each of the adjusted color data. Defined as 1, and the adjusted color data of each adjusted color data value less than or equal to the threshold value is defined as 0, and the set threshold value is set according to the video converter decoding image capability. 如申請專利範圍第1項所述之圖像辨識方法，其中該根據該辨識資料取得對應的該原始資料圖像的步驟係為該辨識資料比對該原始識別顏色資料經二值化處理後所對應的資料，而取得該原始資料圖像。The image recognition method of claim 1, wherein the step of obtaining the corresponding original image according to the identification data is that the identification data is binarized after the original identification color data is processed. The corresponding data is obtained, and the original image is obtained. 一種電子裝置，可電性連接一視訊轉換器，該視訊轉換器用以轉換一原始資料圖像為一播放資料圖像，其中該原始資料圖像之一預設位置上之像素各包括一原始識別顏色資料，該電子裝置包括： 一影像擷取裝置，用以擷取該播放資料圖像； 一處理器，係與該影像擷取裝置電性連接，該處理器用以調整該播放資料圖像之圖面邊長至與該原始資料圖像之圖面邊長實質上相等，以取得一調整後資料圖像，其中該調整後資料圖像相應於該原始資料圖像之該預設位置相同位置上之像素各包括一調整後識別顏色資料；取得該調整後資料圖像後，該處理器更用以將該調整後識別顏色資料經二值化處理，以取得一辨識資料，並根據該辨識資料取得對應的該原始資料圖像。An electronic device electrically connected to a video converter, wherein the video converter converts an original data image into a play data image, wherein each of the pixels in the preset position of the original data image includes an original identification The color data, the electronic device includes: an image capturing device for capturing the image of the playing data; a processor electrically connected to the image capturing device, wherein the processor is configured to adjust the image of the playing data The side of the drawing is substantially equal to the length of the side of the original data image to obtain an adjusted data image, wherein the adjusted data image corresponds to the same position of the preset position of the original data image. Each of the pixels includes an adjusted color data; after obtaining the adjusted data image, the processor is further configured to perform binarization processing on the adjusted color data to obtain an identification data, and according to the identification The data obtains the corresponding original material image. 如申請專利範圍第9項所述之電子裝置，其中該調整後資料圖像之圖面邊長係以該播放資料圖像之圖面邊長乘以該原始資料圖像之圖面邊長與該播放資料圖像之圖面邊長之比值後取得。The electronic device of claim 9, wherein the length of the side of the adjusted data image is multiplied by the length of the side of the image of the broadcast data image by the length of the side of the original data image and Obtained after the ratio of the length of the side of the playback material image. 如申請專利範圍第9項所述之電子裝置，其中該處理器調整該播放資料圖像之圖面邊長包括： 計算取得該原始資料圖像之圖面邊長與該播放資料圖像之圖面邊長的一最小公倍數； 將該最小公倍數除以該播放資料圖像之圖面邊長以得到X； 將該最小公倍數除以該原始資料圖像之圖面邊長以得到Y；以及 將該播放資料圖像之圖面邊長放大X倍再縮小Y倍，而得到該調整後資料圖像之圖面邊長。The electronic device of claim 9, wherein the processor adjusts a side length of the image of the play data to: calculate a picture side length of the original data image and a picture of the play data image a least common multiple of the side length; dividing the least common multiple by the side length of the play data image to obtain X; dividing the least common multiple by the side length of the original data image to obtain Y; The side length of the image of the play data is enlarged by X times and then reduced by Y times, and the side length of the adjusted data image is obtained. 如申請專利範圍第9項所述之電子裝置，其中該處理器調整該播放資料圖像之圖面邊長至與該原始資料圖像之圖面邊長實質上相等係調整該播放資料圖像之圖面寬度或高度至與該原始資料圖像之圖面寬度或高度實質上相等。The electronic device of claim 9, wherein the processor adjusts the side length of the image of the play data to be substantially equal to the length of the side of the original data image, and adjusts the image of the play data. The width or height of the surface is substantially equal to the width or height of the image of the original image. 如申請專利範圍第12項所述之電子裝置，其中該預設位置為複數，且當該複數預設位置位在該原始資料圖像之一側邊緣且沿著該原始資料圖像之圖像寬度方向連續排列時，該處理器調整該播放資料圖像之圖面寬度至與該原始資料圖像之圖面寬度實質上相等。The electronic device of claim 12, wherein the preset position is a plurality, and when the plurality of preset positions are located at one side edge of the original material image and along the image of the original material image When the width direction is continuously arranged, the processor adjusts the picture width of the play data image to be substantially equal to the picture width of the original data image. 如申請專利範圍第12項所述之電子裝置，其中當該預設位置為複數，且該複數預設位置位在該原始資料圖像之一側邊緣且沿著該原始資料圖像之圖像高度方向連續排列時，該處理器調整該播放資料圖像之圖面高度至與該原始資料圖像之圖面高度實質上相等。The electronic device of claim 12, wherein the preset position is a plurality, and the plurality of preset positions are located at one side edge of the original material image and along the image of the original material image When the height direction is continuously arranged, the processor adjusts the height of the image of the play data image to be substantially equal to the height of the image of the original data image. 如申請專利範圍第9項所述之電子裝置，其中將各該調整後識別顏色資料經二值化處理，係將各該調整後識別顏色資料中數值大於一設定閾值之調整後識別顏色資料定義為1，而將各該調整後識別顏色資料數值小於或等於該設定閾值之調整後識別顏色資料定義為0，該設定閾值係根據該視訊轉換器解碼影像能力而設定。The electronic device of claim 9, wherein each of the adjusted color data is binarized, and the adjusted color data of each of the adjusted color data is greater than a set threshold. If the value is 1, the adjusted color data of each adjusted color data value is less than or equal to the set threshold value is defined as 0, and the set threshold value is set according to the video converter decoding image capability. 如申請專利範圍第9項所述之電子裝置，其中該處理器根據該辨識資料取得對應的該原始資料圖像係為該辨識資料比對該原始識別顏色資料經二值化處理後所對應的資料，而取得該原始資料圖像。The electronic device of claim 9, wherein the processor obtains the corresponding original image image according to the identification data as the identification data corresponds to the original identification color data after binarization processing The data is obtained and the original image is obtained. 一種內儲程式之電腦可讀取記錄媒體，當電腦載入該程式並執行後，可完成如申請專利範圍第1至8項所述之圖像辨識方法。A computer-readable recording medium for a built-in program can complete the image recognition method as described in claims 1 to 8 when the computer loads the program and executes it.
TW105107019A 2016-03-08 2016-03-08 Identification method of image frame and electronic device performing the same, computer readable recording medium storing program TWI570635B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
TW105107019A TWI570635B (en) 2016-03-08 2016-03-08 Identification method of image frame and electronic device performing the same, computer readable recording medium storing program
CN201610939729.4A CN107169495B (en) 2016-03-08 2016-11-01 Image identification method and electronic device for executing same

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW105107019A TWI570635B (en) 2016-03-08 2016-03-08 Identification method of image frame and electronic device performing the same, computer readable recording medium storing program

Publications (2)

Publication Number Publication Date
TWI570635B true TWI570635B (en) 2017-02-11
TW201732681A TW201732681A (en) 2017-09-16

Family

ID=58608385

Family Applications (1)

Application Number Title Priority Date Filing Date
TW105107019A TWI570635B (en) 2016-03-08 2016-03-08 Identification method of image frame and electronic device performing the same, computer readable recording medium storing program

Country Status (2)

Country Link
CN (1) CN107169495B (en)
TW (1) TWI570635B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101179710A (en) * 2007-11-30 2008-05-14 浙江工业大学 Intelligent video monitoring apparatus of railway crossing
TW201414062A (en) * 2012-09-27 2014-04-01 Hon Hai Prec Ind Co Ltd Cathode composite material of lithium ion battery
CN104335567A (en) * 2012-05-15 2015-02-04 夏普株式会社 Video-processing device, video-processing method, television receiver, program, and recording medium
TW201528159A (en) * 2014-01-03 2015-07-16 Nat Univ Chin Yi Technology License plate recognition system and method of smart phone with gyroscope sensor included

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5724097A (en) * 1993-10-18 1998-03-03 Mitsubishi Denki Kabushiki Kaisha Adaptive quantization of video based on edge detection
US6351558B1 (en) * 1996-11-13 2002-02-26 Seiko Epson Corporation Image processing system, image processing method, and medium having an image processing control program recorded thereon
CN100418151C (en) * 2002-10-17 2008-09-10 三星电子株式会社 Information storage medium including device-aspect-ratio information, method and apparatus therefor
CN100438635C (en) * 2002-12-16 2008-11-26 皇家飞利浦电子股份有限公司 System for modifying the time-base of a video signal
US7359007B2 (en) * 2004-10-12 2008-04-15 Mediatek Inc. System for format conversion using clock adjuster and method of the same
US20070127909A1 (en) * 2005-08-25 2007-06-07 Craig Mowry System and apparatus for increasing quality and efficiency of film capture and methods of use thereof
CN101083712A (en) * 2006-05-30 2007-12-05 普立尔科技股份有限公司 Method for modifying image using the mode of collecting original image data
JP5472617B2 (en) * 2010-02-09 2014-04-16 富士ゼロックス株式会社 Image processing apparatus, image forming apparatus, and image processing program
KR102327779B1 (en) * 2014-02-21 2021-11-18 삼성전자주식회사 Method for processing image data and apparatus for the same

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101179710A (en) * 2007-11-30 2008-05-14 浙江工业大学 Intelligent video monitoring apparatus of railway crossing
CN104335567A (en) * 2012-05-15 2015-02-04 夏普株式会社 Video-processing device, video-processing method, television receiver, program, and recording medium
TW201414062A (en) * 2012-09-27 2014-04-01 Hon Hai Prec Ind Co Ltd Cathode composite material of lithium ion battery
TW201528159A (en) * 2014-01-03 2015-07-16 Nat Univ Chin Yi Technology License plate recognition system and method of smart phone with gyroscope sensor included

Also Published As

Publication number Publication date
TW201732681A (en) 2017-09-16
CN107169495B (en) 2020-04-14
CN107169495A (en) 2017-09-15

Similar Documents

Publication Publication Date Title
US9600744B2 (en) Adaptive interest rate control for visual search
US8768052B2 (en) Image processing apparatus, image processing method, and non-transitory computer readable medium
WO2020010547A1 (en) Character identification method and apparatus, and storage medium and electronic device
US10176395B2 (en) Automatic correction of skewing of digital images
US9082039B2 (en) Method and apparatus for recognizing a character based on a photographed image
KR102559021B1 (en) Apparatus and method for generating a defect image
JP5847062B2 (en) Image processing device
JP6106808B2 (en) Specify barcode placement in document
CN109447022A (en) A kind of lens type recognition methods and device
US10834281B2 (en) Document size detecting by matching between image of entire document and read size image
CN111709951B (en) Target detection network training method and system, network, device and medium
TWI570635B (en) Identification method of image frame and electronic device performing the same, computer readable recording medium storing program
US8805076B2 (en) Image processing apparatus, image processing method and computer readable medium
US20060126136A1 (en) Image inspecting apparatus, image inspecting method, control program and computer-readable storage medium
US11570331B2 (en) Image processing apparatus, image processing method, and storage medium
US20140300790A1 (en) Image processing apparatus, and non-transitory computer readable medium storing image processing program
JP4839076B2 (en) Video character recognition device, video character recognition method, program, and recording medium
JP4257264B2 (en) Pattern matching device, image quality verification method, and image quality verification program
JP4253265B2 (en) Shadow detection apparatus, shadow detection method and shadow detection program, image processing apparatus using shadow detection apparatus, image processing method using shadow detection method, and image processing program using shadow detection program
US20140347517A1 (en) Image processing apparatus, control method, and recording medium
CN113875247A (en) High dynamic range video format detection
US11900643B2 (en) Object detection method and object detection system
JP7086322B2 (en) Motion analysis device, motion analysis method, and motion analysis program
JP2009124332A (en) Image processor, image processing method and program
JP2007328652A (en) Image processing device and image processing program