TWI726470B - Image recognition system - Google Patents

Image recognition system Download PDF

Info

Publication number
TWI726470B
TWI726470B TW108139637A TW108139637A TWI726470B TW I726470 B TWI726470 B TW I726470B TW 108139637 A TW108139637 A TW 108139637A TW 108139637 A TW108139637 A TW 108139637A TW I726470 B TWI726470 B TW I726470B
Authority
TW
Taiwan
Prior art keywords
image
sub
face
module
database
Prior art date
Application number
TW108139637A
Other languages
Chinese (zh)
Other versions
TW202119275A (en
Inventor
吳秉虔
Original Assignee
華南商業銀行股份有限公司
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 華南商業銀行股份有限公司 filed Critical 華南商業銀行股份有限公司
Priority to TW108139637A priority Critical patent/TWI726470B/en
Application granted granted Critical
Publication of TWI726470B publication Critical patent/TWI726470B/en
Publication of TW202119275A publication Critical patent/TW202119275A/en

Links

Images

Landscapes

  • Image Analysis (AREA)

Abstract

An image recognition system comprises a camera device, a capture module, an image processing module, a facial database, a financial product database, and a computing module. The capture module captures a sub-image comprising one of the five senses of a user from the image acquired by the camera device and calculates a measurable information accordingly. The measurable information comprises a straight line or a region composed of a plurality of feature points. The facial database stores attributes and evaluation values of the measurable information. The financial product database stores a plurality of financial product information and age intervals according to a risk ratio interval. The computing module estimates an age of the user based on the measurable information, obtains the evaluation value from the facial database according to the attribute corresponding to the measurable information, and calculates the risk value accordingly, and obtains a financial product from the financial product database according to the risk value and the age.

Description

影像辨識系統Image recognition system

本發明係關於一種影像辨識系統，特別是一種從影像中取得人臉五官資訊的影像辨識系統。The present invention relates to an image recognition system, in particular to an image recognition system that obtains facial features information from an image.

舉凡銀行、郵局等金融機構在其營業大廳設置多台監視攝影機，用於監視在營業大廳來往活動的人員。For example, banks, post offices and other financial institutions have set up multiple surveillance cameras in their business halls to monitor people moving in and out of the business halls.

然而，這些監視攝影機所拍攝的監視影像通常係用來在事後回顧先前某個特定時間點發生的特殊事件（如蒙面行搶、車手盜領等）。也就是說，金融機構設置的監視系統缺乏依據當前影像即時處理並回報的機制。雖然監視系統長時間運行，但也只是作為一個可能可以嚇阻有心人士的保險裝置。再者，從高處俯拍監視畫面中必然包括各式各樣的人員跟物件，如等待民眾、臨櫃民眾、櫃臺行員、大廳地板、等待座椅、自動櫃員機、補摺機…等；就算安排專人觀看監視影像，從複雜畫面中快速鎖定特定人員的人臉並非易事，更遑論人類容易因疲倦或分心而錯失畫面中的重要資訊。However, the surveillance images taken by these surveillance cameras are usually used to review special events that occurred at a specific point in time afterwards (such as masked robbery, driver theft, etc.). In other words, the monitoring system set up by financial institutions lacks a mechanism for real-time processing and reporting based on current images. Although the surveillance system runs for a long time, it is only used as a safety device that may deter interested people. Furthermore, the surveillance picture taken from a height must include all kinds of people and objects, such as waiting people, people at the counter, counter clerk, lobby floor, waiting seats, ATMs, discount machines... etc.; It is not easy to arrange a dedicated person to watch the surveillance image, and quickly lock the face of a specific person from a complex picture, not to mention that humans are prone to lose important information in the picture due to fatigue or distraction.

此外，對於經常往來的高淨值資產客戶而言，金融機構針對此客層的客戶提供專屬的金融服務，透過客製化的商品投資組合，讓高淨值的客戶得以增加其財富。另一方面，金融機構通常透過廣大的行銷據點協助一般有意願進行財富管理的客戶做中長期的資產規劃，藉由了解客戶現在金流及未來的資金運用規劃進行風險評估，以提出完整的金融產品推薦計畫。In addition, for frequently frequent high-net-worth customers, financial institutions provide exclusive financial services for customers in this class, and through customized product investment portfolios, high-net-worth customers can increase their wealth. On the other hand, financial institutions usually assist customers who are generally willing to conduct wealth management to make mid- and long-term asset planning through their extensive marketing bases. By understanding the customers’ current cash flow and future capital use planning, they conduct risk assessments to propose a complete financial system. Product recommendation plan.

然而，對於單純來到營業廳處理一般金融業務的客戶而言，金融機構的行員或理財專員並無法依據該客戶之五官特徵掌握其是否為潛在具有理財需求的客戶，因此，行員在推銷金融產品時往往流於形式化，無法提供可能符合這類型客戶需求之金融產品，僅能盲目推銷客戶不見得有興趣的項目，徒然浪費雙方的時間與精力。However, for customers who simply come to the business hall to handle general financial services, the bankers or financial specialists of financial institutions cannot know whether the customer is a customer with potential financial needs based on the characteristics of the five senses of the customer. Therefore, the bankers are promoting financial products. Times are often formalized, unable to provide financial products that may meet the needs of this type of customer, and can only blindly promote projects that customers are not necessarily interested in, thus wasting the time and energy of both parties.

有鑑於此，本發明提出一種影像辨識系統，可以從監視攝影機拍攝到的影像中取得人臉影像，並進一步分析五官中的可量測資訊，因此可提升金融產品之銷售成功率及降低客戶因被推薦不適合的產品而導致情緒不佳的機率。In view of this, the present invention proposes an image recognition system that can obtain facial images from images captured by surveillance cameras, and further analyze the measurable information in the five senses, thereby improving the sales success rate of financial products and reducing customer factors Probability of poor mood due to unsuitable products being recommended.

依據本發明一實施例的一種影像辨識系統，包括攝像裝置、擷取模組、影像處理模組、面相資料庫、金融產品資料庫以及運算模組。攝像裝置可取得影像。擷取模組從影像中選取一區塊並取得區塊中一使用者之一人臉影像。影像處理模組電性連接擷取模組。影像處理模組依據人臉影像擷取子影像並依據子影像計算可量測資訊。子影像包括使用者的五官其中一者及其周邊皮膚。可量測資訊包括複數個特徵點組成之一直線或一區域。面相資料庫包括複數個第一表格空間，每個第一表格空間對應於五官類型其中一者並包括複數個第一欄位。每個第一欄位存放可量測資訊之屬性及評估值。屬性包括直線之長度、區域之形狀及顏色。金融產品資料庫包括複數個第二表格空間。這些第二表格空間分別對應於複數個風險比例區間並包括複數個第二欄位。每個第二欄位存放一金融產品及一年紀區間。運算模組通訊連接影像處理模組、面相資料庫及金融產品資料庫。運算模組依據可量測資訊估算使用者之一年紀，依據可量測資訊對應之屬性從面相資料庫中取得評估值，依據評估值計算風險值，依據風險值所對應之些風險比例區間其中一者從金融產品資料庫中選取一第二表格空間，依據年紀所對應之年紀區間從被選取的第二表格空間中選取一第二欄位並輸出。An image recognition system according to an embodiment of the present invention includes a camera device, a capture module, an image processing module, a face database, a financial product database, and a computing module. The camera device can obtain images. The capturing module selects a block from the image and obtains a face image of a user in the block. The image processing module is electrically connected to the capture module. The image processing module captures sub-images based on the face image and calculates measurable information based on the sub-images. The sub-image includes one of the user's facial features and the surrounding skin. The measurable information includes a straight line or a region formed by a plurality of feature points. The face database includes a plurality of first table spaces, and each first table space corresponds to one of the five sense types and includes a plurality of first fields. Each first field stores the attributes and evaluation values of the measurable information. The attributes include the length of the line, the shape and color of the area. The financial product database includes a plurality of second table spaces. These second table spaces respectively correspond to a plurality of risk ratio intervals and include a plurality of second columns. Each second column stores a financial product and one year interval. The computing module communicates with the image processing module, the face database and the financial product database. The computing module estimates the age of the user based on the measurable information, obtains the evaluation value from the face database based on the attributes corresponding to the measurable information, calculates the risk value based on the evaluation value, and calculates the risk value based on the risk ratio corresponding to the risk value. One selects a second table space from the financial product database, and selects and outputs a second column from the selected second table space according to the age interval corresponding to the age.

藉由上述架構，本案所揭露的影像辨識系統可從監視攝影機拍得的複雜影像中快速鎖定特定區域中的人臉影像，並且透過臉部辨識進行分析該人臉影像的年齡及五官特徵中的可量測資訊，再將多個可量測資訊換算為一評估分數。因此，當客戶蒞臨金融機構之營業廳的特定櫃臺時，本案所揭露的影像辨識系統可進一步依據評估分數之範圍推薦適合之金融商品。With the above architecture, the image recognition system disclosed in this case can quickly lock the face image in a specific area from the complex image taken by the surveillance camera, and analyze the age and facial features of the face image through facial recognition. Measurable information, and then convert multiple measurable information into an evaluation score. Therefore, when a customer visits a specific counter in a business hall of a financial institution, the image recognition system disclosed in this case can further recommend suitable financial products based on the range of evaluation scores.

以上之關於本揭露內容之說明及以下之實施方式之說明係用以示範與解釋本發明之精神與原理，並且提供本發明之專利申請範圍更進一步之解釋。The above description of the disclosure and the following description of the implementation manners are used to demonstrate and explain the spirit and principle of the present invention, and to provide a further explanation of the patent application scope of the present invention.

以下在實施方式中詳細敘述本發明之詳細特徵以及優點，其內容足以使任何熟習相關技藝者了解本發明之技術內容並據以實施，且根據本說明書所揭露之內容、申請專利範圍及圖式，任何熟習相關技藝者可輕易地理解本發明相關之目的及優點。以下之實施例係進一步詳細說明本發明之觀點，但非以任何觀點限制本發明之範疇。The detailed features and advantages of the present invention will be described in detail in the following embodiments. The content is sufficient to enable anyone familiar with the relevant art to understand the technical content of the present invention and implement it accordingly, and according to the content disclosed in this specification, the scope of patent application and the drawings. Anyone who is familiar with relevant skills can easily understand the purpose and advantages of the present invention. The following examples further illustrate the viewpoints of the present invention in detail, but do not limit the scope of the present invention by any viewpoint.

請參考圖1，其係繪示本發明一實施例的影像辨識系統10的方塊圖。所述的影像辨識系統10適用於設置在金融機構的營業廳。影像辨識系統10包括：攝像裝置1、擷取模組2、影像處理模組3、面相資料庫4、金融產品資料庫5以及運算模組6。Please refer to FIG. 1, which shows a block diagram of an image recognition system 10 according to an embodiment of the present invention. The image recognition system 10 is suitable for installation in the business hall of a financial institution. The image recognition system 10 includes: a camera device 1, a capturing module 2, an image processing module 3, an aspect database 4, a financial product database 5, and a computing module 6.

攝像裝置1可取得影像。請參考圖2，其係繪示攝像裝置1裝設於金融機構營業廳的俯視示意圖。如圖2所示，攝像裝置1之設置位置可拍攝到金融機構營業廳中特定櫃臺的周邊環境。請參考圖3，其係繪示設置於圖2的攝像裝置1拍攝到的影像，攝像裝置1拍攝到的影像包括在櫃臺周邊的使用者。The imaging device 1 can obtain images. Please refer to FIG. 2, which is a schematic top view of the camera device 1 installed in a business hall of a financial institution. As shown in Fig. 2, the setting position of the camera device 1 can photograph the surrounding environment of a specific counter in the business hall of a financial institution. Please refer to FIG. 3, which shows an image captured by the camera device 1 installed in FIG. 2, and the image captured by the camera device 1 includes users around the counter.

請參考圖1。擷取模組2電性連接攝像裝置1。擷取模組2可依據一區塊進行色彩空間轉換、顏色過濾及邊緣偵測以取得一人臉影像。詳言之，請一併參考圖3。系統管理員可預先從監視畫面中選擇一感興趣區域（Region of Interest）ROI作為前述的區塊，藉此節省擷取模組2針對感興趣區域ROI之外的影像擷取成本。實務上，可依據櫃臺服務人員的視角預先設定畫面中的感興趣區域ROI，如圖3所示。Please refer to Figure 1. The capture module 2 is electrically connected to the camera device 1. The capture module 2 can perform color space conversion, color filtering and edge detection according to a block to obtain a face image. For details, please refer to Figure 3 together. The system administrator can select a Region of Interest ROI from the monitoring screen in advance as the aforementioned block, thereby saving the cost of image capturing for the capturing module 2 outside the ROI of the region of interest. In practice, the ROI of the region of interest in the screen can be preset according to the perspective of the counter service staff, as shown in Figure 3.

依據感興趣區域ROI設定區塊之後，擷取模組2可將該區塊的RGB色彩空間轉換為HSV色彩空間、CIE 1931色彩空間、YIQ色彩空間及YCbCr色彩空間其中一者，藉此減少光線對於後續人臉偵測帶來的影響。在色彩空間轉換完成後，擷取模組2將皮膚顏色與背景顏色分離。詳言之，膚色在轉換後的色彩空間的分佈情況可由一指定方程組定義之。此外，由於金融機構營業廳中的背景物件其顏色固定，故背景色可由另一指定方程組定義之。擷取模組2採用例如大津二值化法（Otsu Thresholding）或直方圖平衡法（Balanced Histogram Thresholding，BHT）找出區塊中所有符合膚色條件的像素點，同時，擷取模組2可一併濾除具有背景顏色的像素點以加速整體的處理速度。After setting the block according to the ROI of the region of interest, the capture module 2 can convert the RGB color space of the block into one of HSV color space, CIE 1931 color space, YIQ color space and YCbCr color space, thereby reducing light The impact on subsequent face detection. After the color space conversion is completed, the capture module 2 separates the skin color from the background color. In detail, the distribution of skin color in the converted color space can be defined by a specified equation system. In addition, because the color of the background object in the business hall of the financial institution is fixed, the background color can be defined by another specified equation set. The capture module 2 uses, for example, the Otsu Thresholding method or the Balanced Histogram Thresholding (BHT) method to find all the pixels in the block that meet the skin color condition. At the same time, the capture module 2 can be And filter out pixels with background color to speed up the overall processing speed.

於一實施例中，針對二值化後的影像，擷取模組2可採用形態學（morphology）上的膨脹（dilation）算子和腐蝕（erosion）算子消除人臉區域外的雜訊。具體而言，擷取模組2可進行先膨脹後腐蝕的閉運算（Closing operation）然後再進行先腐蝕後膨脹的開運算（Open operation），藉此可凸顯影像中五官周圍的輪廓。In one embodiment, for the binarized image, the capture module 2 can use a morphology (dilation) operator and an erosion (erosion) operator to eliminate noise outside the face area. Specifically, the capturing module 2 can perform a closing operation (closing operation) of first expansion and then corrosion, and then an open operation of first corrosion and then expansion, so as to highlight the contours around the five sense organs in the image.

針對消除雜訊後的影像區塊，擷取模組2依據人臉的幾何模型圈選出區塊中的人臉影像。所述的幾何模型可依據一般人臉的高度與寬度的比值的區間定義之，例如：0.79≤人臉高度/人臉寬度≤2.95。For the image block after the noise is eliminated, the capture module 2 circles the face image in the block according to the geometric model of the face. The geometric model can be defined based on the interval of the ratio of the height to the width of a general face, for example: 0.79≤face height/face width≤2.95.

於另一實施例中，擷取模組2例如採用坎尼算子（Canny filter）、索伯算子（Sobel filter）或Prewitt算子，藉此進行人臉影像的邊緣偵測，進一步輸出一人臉影像。In another embodiment, the capturing module 2 uses, for example, Canny filter, Sobel filter or Prewitt operator to detect the edge of the face image and further output a person Face image.

於又一實施例中，擷取模組2將基於YUV顏色編碼方法的區塊影像中進一步分成複數個重疊的小型區域，針對這些區域中明亮度之數值（即Y元素），計算每個小型區域在水平方向、垂直方向及兩對角方向的邊緣強度值，依據計算出的這些強度值及一門檻值互相比對而得出人臉邊緣，進一步輸出人臉影像。In another embodiment, the capture module 2 further divides the block image based on the YUV color coding method into a plurality of overlapping small areas, and calculates each small area for the brightness value (ie Y element) in these areas. The edge intensity values of the region in the horizontal direction, the vertical direction and the two diagonal directions are compared with each other according to the calculated intensity values and a threshold value to obtain the face edge, and then the face image is further output.

於再一實施例中，擷取模組2依據事先訓練好的特徵臉（eigenface）之影像樣本進行比對，進而輸出人臉影像。實務上，金融機構可採用眾多客戶開戶時所留存的具有不同人臉的影像檔進行主成分分析（Principal Component Analysis，PCA）獲得一組特徵臉的向量做為前述的影像樣本。In still another embodiment, the capturing module 2 compares the image samples of the eigenface that has been trained in advance, and then outputs the face image. In practice, financial institutions can use image files with different faces saved by many customers when opening accounts to perform Principal Component Analysis (PCA) to obtain a set of vectors of characteristic faces as the aforementioned image samples.

實務上，擷取模組2例如係數位訊號處理器（digital signal processor）、特殊應用積體電路（application specific integrated circuit，ASIC）、數位邏輯電路、現場可程式邏輯閘陣列（field programmable gate array，FPGA） 或其它可執行上述的人臉影像擷取功能的硬體元件。In practice, the capture module 2 is, for example, a digital signal processor (digital signal processor), an application specific integrated circuit (ASIC), a digital logic circuit, and a field programmable gate array (field programmable gate array). FPGA) or other hardware components that can perform the aforementioned facial image capture function.

影像處理模組3電性連接擷取模組2。影像處理模組3依據人臉影像取得複數個特徵點，並依據這些特徵點的分佈方式擷取子影像，再依據子影像計算可量測資訊。The image processing module 3 is electrically connected to the capturing module 2. The image processing module 3 obtains a plurality of feature points according to the face image, and captures sub-images according to the distribution of these feature points, and then calculates measurable information based on the sub-images.

於一實施例中，影像處理模組3採用連通分量標記（connected-component labeling）演算法，找出影像中相連接的像素，以便標記人臉影像中五官的座標作為特徵點。In one embodiment, the image processing module 3 uses a connected-component labeling algorithm to find connected pixels in the image, so as to mark the coordinates of the facial features in the face image as feature points.

於另一實施例中，影像處理模組3採用主動形狀模型（Active Shape Model）或主動外觀模型（Active Appearance Models，AAM），一次計算出人臉影像中五官特徵點的座標。In another embodiment, the image processing module 3 uses Active Shape Model (Active Shape Model) or Active Appearance Models (AAM) to calculate the coordinates of the facial features in the face image at one time.

影像處理模組3依據特徵點所擷取的子影像包括使用者的五官其中一者及其周邊皮膚。在一實施例中，子影像係第一子影像，第一子影像包括使用者的眼及其周邊皮膚。於另一實施例中，影像處理模組3更依據人臉影像分別擷取第二子影像、第三子影像、第四子影像及第五子影像。第二子影像包括使用者的眉及其周邊皮膚，第三子影像包括使用者的鼻及其周邊皮膚、第四子影像包括使用者的口及其周邊皮膚，第五子影像包括使用者的耳。The sub-images captured by the image processing module 3 according to the feature points include one of the facial features of the user and the surrounding skin. In one embodiment, the sub-image is the first sub-image, and the first sub-image includes the user's eyes and surrounding skin. In another embodiment, the image processing module 3 further captures the second sub-image, the third sub-image, the fourth sub-image, and the fifth sub-image according to the face image. The second sub-image includes the user’s eyebrows and its surrounding skin, the third sub-image includes the user’s nose and its surrounding skin, the fourth sub-image includes the user’s mouth and its surrounding skin, and the fifth sub-image includes the user’s ear.

在取得子影像之後，影像處理模組3依據子影像計算可量測資訊。所述的可量測資訊包括複數個特徵點組成之一直線或一區域、區域面積。可量測資訊包括眼睛形狀、雙眼間距、眉毛長度、眉毛間距、鼻翼寬度、鼻梁長度、上唇厚度、下唇厚度、耳朵形狀、耳朵顏色，以及位於五官周邊皮膚的皺紋長度、皺紋深度和皮膚班點等。After obtaining the sub-image, the image processing module 3 calculates the measurable information according to the sub-image. The measurable information includes a straight line or a region or region area formed by a plurality of feature points. Measurable information includes eye shape, eye distance, eyebrow length, eyebrow distance, nose width, nose bridge length, upper lip thickness, lower lip thickness, ear shape, ear color, and wrinkle length, wrinkle depth and skin surrounding the facial features Wait for the class.

面相資料庫4包括複數個第一表格空間，每個第一表格空間對應於五官類型其中一者並包括複數個第一欄位。具體來說，每個表格空間對應到上述可量測資訊的一種類型。例如表格空間A係關聯於眼睛形狀、表格空間B係關聯於雙眼間距。每個第一欄位存放可量測資訊之屬性、評估值及一權重值。屬性包括直線之長度、區域之形狀及顏色。承前例，表格空間A的每個欄位所存放的屬性係對應到不同的眼睛形狀，例如：杏眼、丹鳳眼、上斜眼、細長眼、圓眼、垂眼、三角眼等，每一種眼睛形狀對應到一評估值。表格空間B的每個欄位所存放的屬性係對應到不同的雙眼間距，例如1.1~1.3公分、1.3~1.5公分、1.5~1.7公分等。The face database 4 includes a plurality of first table spaces, and each first table space corresponds to one of the five sense types and includes a plurality of first fields. Specifically, each table space corresponds to one type of the above-mentioned measurable information. For example, table space A is related to the shape of the eyes, and table space B is related to the distance between the eyes. Each first field stores the attributes of the measurable information, the evaluation value and a weight value. The attributes include the length of the line, the shape and color of the area. Following the previous example, the attributes stored in each column of table space A correspond to different eye shapes, such as apricot eye, red phoenix eye, upward slanting eye, slender eye, round eye, downcast eye, triangular eye, etc. Each eye shape corresponds to To an evaluation value. The attributes stored in each column of table space B correspond to different binocular distances, such as 1.1 to 1.3 cm, 1.3 to 1.5 cm, 1.5 to 1.7 cm, etc.

面相資料庫4的多個第一欄位各自評估值及權重值，係預先經由另一運算模組運行一深度學習演算法得出。詳言之，金融機構可依據原有的客戶影像資料庫、客戶填寫的投資人風險屬性分析問卷調查表以及客戶投資的金融產品項目等大數據作為原始訓練集，透過遞歸神經網路（Recursice Neural Network，RNN）或長短期記憶神經網路（Long Short Term Memory，LSTM）獲取各種金融產品類型所對應的特定五官類型，進而計算出每個欄位所存放的評估值及權重值。所述的評估值關聯於投資人願意負擔的風險比例，權重值代表綜合多種五官可量測資訊考慮時各個類型應佔的比重。The respective evaluation values and weight values of the first columns of the face database 4 are obtained by running a deep learning algorithm through another computing module in advance. In detail, financial institutions can use big data such as the original customer image database, investor risk attribute analysis questionnaires filled out by customers, and financial product projects invested by customers as the original training set. Network (RNN) or Long Short Term Memory (LSTM) to obtain the specific facial features corresponding to various types of financial products, and then calculate the evaluation value and weight value stored in each field. The evaluation value is related to the risk ratio that the investor is willing to bear, and the weight value represents the proportion of each type when considering the comprehensive measurable information of various facial features.

金融產品資料庫5包括複數個第二表格空間。這些第二表格空間分別對應於複數個風險比例區間並包括複數個第二欄位，每個第二欄位存放一金融產品及一年紀區間。舉例來說，表格空間C對應的風險比例區間為0~6，其風險屬性典型分類為「保守型」，代表投資人基本上不願承擔任何投資風險，適合的金融產品偏向報酬來自利息收入的產品；表格空間D對應的風險比例區間為7~13，其風險屬性典型分類為「非常謹慎型」，代表投資人基本上可接受輕微的損失，以換取輕微的潛在投資報酬，適合的金融產品為金融機構評定為低風險的項目。需注意的是，上述風險比例區間之邊界值，係預先經由另一運算模組運行一深度學習演算法得出。The financial product database 5 includes a plurality of second table spaces. These second table spaces respectively correspond to a plurality of risk ratio intervals and include a plurality of second columns, and each second column stores a financial product and a one-year interval. For example, the risk ratio range corresponding to table space C is 0~6, and its risk attribute is typically classified as "conservative", which means that investors are basically unwilling to bear any investment risks. Suitable financial products prefer to pay from interest income. Product; the corresponding risk ratio range of table space D is 7~13, and its risk attribute is typically classified as "very cautious", which means that investors can basically accept slight losses in exchange for a slight potential return on investment, suitable for financial products Projects rated as low-risk by financial institutions. It should be noted that the boundary value of the aforementioned risk ratio interval is obtained by running a deep learning algorithm through another computing module in advance.

運算模組6通訊連接影像處理模組3、面相資料庫4及金融產品資料庫5。運算模組6依據可量測資訊估算使用者之一年紀。詳言之，運算模組6主要依據位於五官周邊皮膚的皺紋長度、皺紋深度和皮膚班點等可量測資訊進行年紀之估算，特別是位於眉毛上方的抬頭紋、鼻子兩側的法令紋以及眼睛周邊的魚尾紋。影像處理模組3採用Canny邊緣偵測器技術偵測皺紋之紋理，並設定適當臨界值以進行年齡判斷。另一方面，由於人臉皮膚會隨著老化而呈現不同的班點特徵，因此可針對人臉影像的皮膚區塊進行膚色的分割以作為識別年齡之輔助方法。具體來說，適當選擇Y、C b及C r色彩空間上之參數臨界值，並對擷取模組2輸出的人臉影像進行檢測，可偵測出老人斑。舉例來說，若人臉影像的特定區塊符合以下公式：(24≤Y≤124)且(113≤C b≤140)且(115≤C r≤143)，則可判斷該指定區塊具有老人斑。運算模組6可進一步依據老人斑的顏色及個數並依據抬頭紋、法令紋及魚尾紋的數量估算使用者的年紀。 The computing module 6 is communicatively connected to the image processing module 3, the face database 4 and the financial product database 5. The computing module 6 estimates the age of the user based on the measurable information. In detail, the calculation module 6 mainly estimates the age based on the wrinkle length, wrinkle depth, and skin point of the skin around the facial features, especially the forehead wrinkles above the eyebrows, the nasolabial wrinkles on both sides of the nose, and Crow's feet around the eyes. The image processing module 3 uses Canny edge detector technology to detect the texture of wrinkles, and sets appropriate thresholds for age determination. On the other hand, since the facial skin will present different class features with aging, the skin color segmentation can be performed for the skin area of the facial image as an auxiliary method for identifying the age. Specifically, by appropriately selecting the critical values of the parameters in the Y, C b, and C r color spaces, and detecting the face image output by the capturing module 2, age spots can be detected. For example, if a specific block of a face image meets the following formula: (24≤Y≤124) and (113≤C b ≤140) and (115≤C r ≤143), it can be determined that the specified block has Age spots. The computing module 6 can further estimate the age of the user based on the color and number of age spots and the number of forehead lines, nasolabial lines, and crow's feet.

運算模組6依據五官的可量測資訊對應之屬性從面相資料庫4中取得一或數個評估值，依據評估值計算風險值，依據風險值所對應之些風險比例區間其中一者從金融產品資料庫5中選取一第二表格空間，依據年紀所對應之年紀區間從被選取的第二表格空間中選取一第二欄位並輸出。實務上，運算模組6依據第一子影像、第二子影像、第三子影像、第四子影像及第五子影像各自的可量測資訊對應之屬性從面相資料庫4中取得五評估值及五權重值，且依據五評估值及五權重值計算風險值。詳言之，運算模組6先依據使用者五官的特徵分別得出風險評估值（例如眼、眉、鼻、耳各自對應的風險評估值分別為A 1、A 2、A 3、A 4及A 5），然後根據五官屬性各自對應的權重值（例如A 1對應W 1、A 2對應W 2…、A 5對應W 5），再將這些風險評估值依據其對應的權重值予以加總得到該使用者的一綜合風險評估值（例如為A 1*W 1+A 2*W 2+A 3*W 3+A 4*W 4+A 5*W 5）。運算模組6依據此綜合風險評估值在金融產品資料庫5中取得對應的金融產品列表，然後依據運算模組估算的使用者年紀取得一推薦金融產品。 The arithmetic module 6 obtains one or several evaluation values from the face database 4 according to the attributes corresponding to the measurable information of the five sense organs, calculates the risk value according to the evaluation value, and calculates the risk value according to the risk value corresponding to one of the risk ratio ranges from the financial A second table space is selected from the product database 5, and a second column is selected and output from the selected second table space according to the age interval corresponding to the age. In practice, the computing module 6 obtains five evaluations from the surface image database 4 according to the attributes corresponding to the measurable information of the first, second, third, fourth, and fifth sub-images. The risk value is calculated based on the five evaluation value and the five weight value. In detail, the calculation module 6 firstly obtains risk assessment values according to the features of the user’s five senses (for example, the corresponding risk assessment values of the eyes, eyebrows, nose, and ears are A 1 , A 2 , A 3 , A 4 and A 5 ), and then add up these risk assessment values according to their corresponding weight values according to the respective weight values of the five sense attributes (for example, A 1 corresponds to W 1 , A 2 corresponds to W 2 …, A 5 corresponds to W 5) Obtain a comprehensive risk assessment value of the user (for example, A 1 *W 1 +A 2 *W 2 +A 3 *W 3 +A 4 *W 4 +A 5 *W 5 ). The calculation module 6 obtains the corresponding financial product list in the financial product database 5 according to the comprehensive risk assessment value, and then obtains a recommended financial product according to the user age estimated by the calculation module.

綜合以上所述，本發明所揭露的影像辨識系統可從監視攝影機拍得的複雜影像中快速鎖定特定區域中的人臉影像，並且透過臉部辨識進行分析該人臉影像的年齡及五官特徵中的可量測資訊，再將多個可量測資訊換算為一評估分數。因此，當客戶蒞臨金融機構之營業廳的特定櫃臺時，本案所揭露的影像辨識系統可進一步依據評估分數之範圍推薦適合之金融商品。In summary, the image recognition system disclosed in the present invention can quickly lock a face image in a specific area from a complex image taken by a surveillance camera, and analyze the age and facial features of the face image through facial recognition. The measurable information of, and then convert multiple measurable information into an evaluation score. Therefore, when a customer visits a specific counter in a business hall of a financial institution, the image recognition system disclosed in this case can further recommend suitable financial products based on the range of evaluation scores.

雖然本發明以前述之實施例揭露如上，然其並非用以限定本發明。在不脫離本發明之精神和範圍內，所為之更動與潤飾，均屬本發明之專利保護範圍。關於本發明所界定之保護範圍請參考所附之申請專利範圍。Although the present invention is disclosed in the foregoing embodiments, it is not intended to limit the present invention. All changes and modifications made without departing from the spirit and scope of the present invention fall within the scope of the patent protection of the present invention. For the scope of protection defined by the present invention, please refer to the attached scope of patent application.

10:影像辨識系統 1:攝像裝置 2:擷取模組 3:影像處理模組 4:面相資料庫 5:金融產品資料庫 6:運算模組 ROI:感興趣區域 10: Image recognition system 1: camera device 2: Capture module 3: Image processing module 4: Face database 5: Financial product database 6: Computing module ROI: region of interest

圖1係依據本發明一實施例的影像辨識系統所繪示的架構圖。 圖2係依據本發明一實施例的攝像裝置的設置於金融機構營業廳的俯視示意圖。 圖3係依據本發明一實施例的攝像裝置拍攝的影像示意圖。 FIG. 1 is a structural diagram of an image recognition system according to an embodiment of the present invention. 2 is a schematic top view of a camera device installed in a business hall of a financial institution according to an embodiment of the present invention. FIG. 3 is a schematic diagram of an image captured by a camera device according to an embodiment of the present invention.

10:影像辨識系統 10: Image recognition system

1:攝像裝置 1: camera device

2:擷取模組 2: Capture module

3:影像處理模組 3: Image processing module

4:面相資料庫 4: Face database

5:金融產品資料庫 5: Financial product database

6:運算模組 6: Computing module

Claims (6)

一種影像辨識系統，包括：一攝像裝置，用以取得單一影像；一擷取模組，通訊連接該攝像裝置，該擷取裝置用以從該影像選取一區塊並取得該區塊中一使用者之一人臉影像，其中該擷取模組更用以依據該區塊進行色彩空間轉換、顏色過濾及邊緣偵測以取得該人臉影像，該擷取模組更用以轉換該區塊之一色彩空間為HSV色彩空間、CIE 1931色彩空間、YIQ色彩空間及YCbCr色彩空間其中一者；一影像處理模組，通訊連接該擷取模組，該影像處理模組依據該人臉影像擷取一子影像並依據單獨的該子影像計算一可量測資訊，其中單獨的該子影像包括該使用者的五官其中一者及其周邊皮膚，該可量測資訊包括複數個特徵點組成之一直線及一區域；一面相資料庫，包括複數個第一表格空間，每一該些第一表格空間對應於五官類型其中一者並包括複數個第一欄位，每一該些第一欄位存放該可量測資訊之一屬性及一評估值，其中該屬性包括該直線之一長度、該區域之一形狀及一顏色；一金融產品資料庫，包括複數個第二表格空間，該些第二表格空間分別對應於複數個風險比例區間並包括複數個第二欄位，每一該些第二欄位存放一金融產品及一年紀區間；以及一運算模組，通訊連接該影像處理模組、該面相資料庫及該金融產品資料庫，該運算模組依據該可量測資訊估算該使用者之一年紀，依據該可量測資訊對應之該屬性從該面相資料庫中取得該評估值，依據該評估值計 算一風險值，依據該風險值所對應之該些風險比例區間其中一者從該金融產品資料庫中選取該些第二表格空間其中一者，依據該年紀所對應之該年紀區間從被選取的該第二表格空間中選取一第二欄位並輸出，其中該子影像係一第一子影像，該第一子影像包括該使用者的眼及其周邊皮膚；該影像處理模組更依據該人臉影像分別擷取一第二子影像、一第三子影像、一第四子影像及一第五子影像，該第二子影像包括該使用者的眉及其周邊皮膚，該第三子影像包括該使用者的鼻及其周邊皮膚、該第四子影像包括該使用者的口及其周邊皮膚，該第五子影像包括該使用者的耳；該可量測資訊更包括眼睛形狀、雙眼間距、眉毛長度、眉毛間距、鼻翼寬度、鼻梁長度、上唇厚度、下唇厚度、耳朵形狀及耳朵顏色；該面相資料庫的每一該些第一欄位更存放該可量測資訊之一權重值；該運算模組依據該第一子影像、該第二子影像、該第三子影像、該第四子影像及該第五子影像各自的該可量測資訊對應之該屬性從該面相資料庫中取得五評估值及五權重值，且依據該五評估值及該五權重值計算該風險值；以及該面相資料庫的該些第一欄位之該些評估值及該些權重值，以及該金融產品資料庫之該些風險比例區間之邊界值，係預先經由另一運算模組運行一深度學習演算法得出。 An image recognition system includes: a camera device for obtaining a single image; a capturing module, which is communicatively connected to the camera device, and the capturing device is used for selecting a block from the image and obtaining one of the blocks for use One of the face images, wherein the capture module is used to perform color space conversion, color filtering and edge detection according to the block to obtain the face image, and the capture module is further used to convert the block A color space is one of HSV color space, CIE 1931 color space, YIQ color space and YCbCr color space; an image processing module, which is communicatively connected to the capture module, and the image processing module captures the face image A sub-image and calculate a measurable information based on the single sub-image, where the single sub-image includes one of the facial features of the user and the surrounding skin, and the measurable information includes a straight line composed of a plurality of feature points And an area; a face database, including a plurality of first table spaces, each of the first table spaces corresponds to one of the five sense types and includes a plurality of first fields, and each of the first fields is stored An attribute and an evaluation value of the measurable information, wherein the attribute includes a length of the straight line, a shape and a color of the area; a financial product database includes a plurality of second table spaces, the second The table space respectively corresponds to a plurality of risk ratio intervals and includes a plurality of second fields, each of which stores a financial product and one year interval; and a computing module, which is communicatively connected to the image processing module, The face database and the financial product database, the calculation module estimates the age of the user based on the measurable information, and obtains the evaluation value from the face database according to the attribute corresponding to the measurable information, According to the evaluation value Calculate a risk value, select one of the second table spaces from the financial product database according to one of the risk ratio intervals corresponding to the risk value, and select one of the second table spaces according to the age interval corresponding to the age Select a second field from the second table space of the, and output, wherein the sub-image is a first sub-image, and the first sub-image includes the user's eye and its surrounding skin; the image processing module is further based on The face image captures a second sub-image, a third sub-image, a fourth sub-image, and a fifth sub-image. The second sub-image includes the user's eyebrows and surrounding skin, and the third The sub-image includes the user's nose and its surrounding skin, the fourth sub-image includes the user's mouth and its surrounding skin, the fifth sub-image includes the user's ears; the measurable information further includes the shape of the eyes , Eye distance, eyebrow length, eyebrow distance, nose width, nose bridge length, upper lip thickness, lower lip thickness, ear shape and ear color; each of the first fields of the facial database also stores the measurable information A weight value; the calculation module corresponds to the attribute corresponding to the measurable information of the first sub-image, the second sub-image, the third sub-image, the fourth sub-image, and the fifth sub-image Obtain five assessment values and five weight values from the face database, and calculate the risk value based on the five assessment values and the five weight values; and the assessment values and the first columns of the face database The weight values and the boundary values of the risk ratio intervals of the financial product database are obtained by running a deep learning algorithm through another computing module in advance. 如請求項1所述的影像辨識系統，其中該擷取模組更用以依據一人臉幾何模型圈選出該區塊中的該人臉影像，其中該人臉幾何模型關聯於人臉高度與寬度的比值。 The image recognition system according to claim 1, wherein the capture module is further used to circle the face image in the block according to a geometric model of the face, wherein the geometric model of the face is related to the height and width of the face Ratio. 如請求項1所述的影像辨識系統，其中該擷取模組更用以依據坎尼算子、索伯算子或Prewitt算子進行邊緣偵測以輸出該人臉影像。 The image recognition system according to claim 1, wherein the capturing module is further used for edge detection according to Canney operator, Sauber operator or Prewitt operator to output the face image. 如請求項1所述的影像辨識系統，其中該擷取模組依據一特徵臉樣本進行比對而輸出該人臉影像。 The image recognition system according to claim 1, wherein the capturing module outputs the face image according to a characteristic face sample comparison. 如請求項1所述的影像辨識系統，其中該影像處理模組依據一主動形狀模型或一主動外觀模型計算該人臉影像中之五官特徵點座標。 The image recognition system according to claim 1, wherein the image processing module calculates the coordinates of the facial features in the face image according to an active shape model or an active appearance model. 如請求項1所述的影像辨識系統，其中該深度學習演算法係長短期記憶神經網路或遞歸神經網路，且該深度學習演算法之輸入層包括：客戶影像資料庫、投資人風險屬性分析問卷調查表以及投資金融產品項目，且該深度學習演算法之輸出層包括每一該些第一欄位所存放的該評估值及該權重值。 The image recognition system according to claim 1, wherein the deep learning algorithm is a long and short-term memory neural network or a recurrent neural network, and the input layer of the deep learning algorithm includes: customer image database, investor risk attribute analysis Questionnaires and investment financial product items, and the output layer of the deep learning algorithm includes the evaluation value and the weight value stored in each of the first fields.
TW108139637A 2019-11-01 2019-11-01 Image recognition system TWI726470B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
TW108139637A TWI726470B (en) 2019-11-01 2019-11-01 Image recognition system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW108139637A TWI726470B (en) 2019-11-01 2019-11-01 Image recognition system

Publications (2)

Publication Number Publication Date
TWI726470B true TWI726470B (en) 2021-05-01
TW202119275A TW202119275A (en) 2021-05-16

Family

ID=77020802

Family Applications (1)

Application Number Title Priority Date Filing Date
TW108139637A TWI726470B (en) 2019-11-01 2019-11-01 Image recognition system

Country Status (1)

Country Link
TW (1) TWI726470B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109345370A (en) * 2018-08-29 2019-02-15 中国建设银行股份有限公司 Risk Forecast Method, device, terminal and readable medium based on recognition of face
CN109829358A (en) * 2018-12-14 2019-05-31 深圳壹账通智能科技有限公司 Micro- expression loan control method, device, computer equipment and storage medium
TWM582163U (en) * 2019-04-24 2019-08-11 阿爾發金融科技股份有限公司 Face recognition financial management planning system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109345370A (en) * 2018-08-29 2019-02-15 中国建设银行股份有限公司 Risk Forecast Method, device, terminal and readable medium based on recognition of face
CN109829358A (en) * 2018-12-14 2019-05-31 深圳壹账通智能科技有限公司 Micro- expression loan control method, device, computer equipment and storage medium
TWM582163U (en) * 2019-04-24 2019-08-11 阿爾發金融科技股份有限公司 Face recognition financial management planning system

Also Published As

Publication number Publication date
TW202119275A (en) 2021-05-16

Similar Documents

Publication Publication Date Title
CN108038456B (en) Anti-deception method in face recognition system
Sankowski et al. Reliable algorithm for iris segmentation in eye image
EP3467709A1 (en) Face recognition method and system for personal identification and authentication
US20170169297A1 (en) Computer-vision-based group identification
CN110097034A (en) A kind of identification and appraisal procedure of Intelligent human-face health degree
CN110210448B (en) Intelligent face skin aging degree identification and evaluation method
TWM592541U (en) Image recognition system
CN101339603A (en) Method for selecting qualified iris image from video frequency stream
CN111209818A (en) Video individual identification method, system, equipment and readable storage medium
Sarode et al. Facial expression recognition
JP2013058060A (en) Person attribute estimation device, person attribute estimation method and program
CN106778637B (en) Statistical method for man and woman passenger flow
CN106558061A (en) A kind of cash register loss prevention method and system based on cloud computing
AU2017231602A1 (en) Method and system for visitor tracking at a POS area
Devi et al. Driver drowsiness detection using skin color algorithm and circular hough transform
JP2003242486A (en) Person attribute estimating device
TWI726470B (en) Image recognition system
TWI748908B (en) Image recognition system based on features points of five senses
TWI765632B (en) Image recognition system based on edge detection
TWI765633B (en) Image recognition system based on face geometric model
Lee et al. An intelligent image-based customer analysis service
TWM593011U (en) Image recognition system
Sikandar et al. An efficient method for detecting covered face scenarios in ATM surveillance camera
TWI718743B (en) Image recognition system
Gizatdinova et al. Automatic edge-based localization of facial features from images with complex facial expressions