TWI615780B - Fingerprint image processing method and device - Google Patents
Fingerprint image processing method and device Download PDFInfo
- Publication number
- TWI615780B TWI615780B TW104136796A TW104136796A TWI615780B TW I615780 B TWI615780 B TW I615780B TW 104136796 A TW104136796 A TW 104136796A TW 104136796 A TW104136796 A TW 104136796A TW I615780 B TWI615780 B TW I615780B
- Authority
- TW
- Taiwan
- Prior art keywords
- fingerprint
- image
- features
- fingerprint image
- processor
- Prior art date
Links
Abstract
一種指紋影像處理方法與裝置，所述指紋影像處理方法，包括下列步驟。利用第一搜尋演算法從指紋影像中擷取出多個第一指紋特徵。對指紋影像執行反白處理，以取得反白指紋影像。利用第一搜尋演算法從反白指紋影像中擷取出多個參考特徵。參照所述多個參考特徵的座標，從指紋影像中取得多個第二指紋特徵。A fingerprint image processing method and apparatus, the fingerprint image processing method, comprising the following steps. A plurality of first fingerprint features are extracted from the fingerprint image by using a first search algorithm. Perform a whitening process on the fingerprint image to obtain a reverse fingerprint image. A plurality of reference features are extracted from the reverse fingerprint image using the first search algorithm. Referring to the coordinates of the plurality of reference features, a plurality of second fingerprint features are obtained from the fingerprint image.
Description
本發明是有關於一種處理方法與裝置，且特別是有關於一種指紋影像處理方法與裝置。The present invention relates to a processing method and apparatus, and in particular to a fingerprint image processing method and apparatus.
近年來，指紋辨識技術已廣泛地應用在各種電子裝置，以藉此強化裝置本身的防偽能力與安全性。在指紋辨識技術中，指紋特徵的正確與否將影響整個裝置的精確度。此外，現有的指紋影像處理裝置往往必須透過不同的搜尋演算法，才能從指紋影像中擷取不同的兩指紋特徵。因此，現有的指紋影像處理裝置往往必須耗費較久的運算時間才能擷取出多個指紋特徵，進而降低指紋特徵的擷取速度，從而造成指紋影像處理裝置在使用上的不便性。In recent years, fingerprint identification technology has been widely applied to various electronic devices to enhance the anti-counterfeiting capability and security of the device itself. In the fingerprint identification technology, the correctness of the fingerprint feature will affect the accuracy of the entire device. In addition, existing fingerprint image processing devices often have to use different search algorithms to extract different fingerprint features from the fingerprint image. Therefore, the existing fingerprint image processing device often has to take a long time to extract a plurality of fingerprint features, thereby reducing the speed of capturing fingerprint features, thereby causing inconvenience in use of the fingerprint image processing device.
本發明提供一種指紋影像處理方法與裝置，可利用同一搜尋演算法擷取出不同的兩指紋特徵，進而可增加指紋特徵的擷取速度，並有助於提升指紋影像處理裝置在使用上的便利性。The invention provides a fingerprint image processing method and device, which can extract different fingerprint features by using the same search algorithm, thereby increasing the speed of capturing fingerprint features and facilitating the convenience of use of the fingerprint image processing device. .
本發明的指紋影像處理方法，包括下列步驟。利用第一搜尋演算法從指紋影像中擷取出多個第一指紋特徵。對指紋影像執行反白處理，以取得反白指紋影像。利用第一搜尋演算法從反白指紋影像中擷取出多個參考特徵。參照所述多個參考特徵的座標，從指紋影像中取得多個第二指紋特徵。The fingerprint image processing method of the present invention comprises the following steps. A plurality of first fingerprint features are extracted from the fingerprint image by using a first search algorithm. Perform a whitening process on the fingerprint image to obtain a reverse fingerprint image. A plurality of reference features are extracted from the reverse fingerprint image using the first search algorithm. Referring to the coordinates of the plurality of reference features, a plurality of second fingerprint features are obtained from the fingerprint image.
本發明的指紋影像處理裝置，包括指紋感測器與處理器。指紋感測器產生原始影像。處理器透過前置程序將原始影像轉換成指紋影像，並利用第一搜尋演算法從指紋影像中擷取出多個第一指紋特徵。此外，處理器對指紋影像執行反白處理以取得反白指紋影像。再者，處理器利用第一搜尋演算法從反白指紋影像中擷取出多個參考特徵，並參照所述多個參考特徵的座標從指紋影像中取得多個第二指紋特徵。The fingerprint image processing device of the present invention comprises a fingerprint sensor and a processor. The fingerprint sensor produces the original image. The processor converts the original image into a fingerprint image through a pre-program, and extracts a plurality of first fingerprint features from the fingerprint image by using a first search algorithm. In addition, the processor performs a whitening process on the fingerprint image to obtain a reverse fingerprint image. Furthermore, the processor extracts a plurality of reference features from the reverse fingerprint image by using the first search algorithm, and obtains a plurality of second fingerprint features from the fingerprint image by referring to the coordinates of the plurality of reference features.
基於上述，本發明利用第一搜尋演算法從指紋影像中擷取出多個第一指紋特徵，並利用從反白指紋影像中所擷取出之參考特徵的座標，從指紋影像中取得多個第二指紋特徵。換言之，本發明可利用相同的搜尋演算法從指紋影像中取得第一指紋特徵與第二指紋特徵，因此可增加指紋特徵的擷取速度，並有助於提升指紋影像處理裝置在使用上的便利性。Based on the above, the present invention uses the first search algorithm to extract a plurality of first fingerprint features from the fingerprint image, and obtains a plurality of second images from the fingerprint image by using coordinates of the reference features extracted from the reverse fingerprint image. Fingerprint feature. In other words, the present invention can utilize the same search algorithm to obtain the first fingerprint feature and the second fingerprint feature from the fingerprint image, thereby increasing the capture speed of the fingerprint feature and facilitating the use of the fingerprint image processing device. Sex.
為讓本發明的上述特徵和優點能更明顯易懂，下文特舉實施例，並配合所附圖式作詳細說明如下。The above described features and advantages of the invention will be apparent from the following description.
圖1為依據本發明一實施例之指紋影像處理裝置的示意圖。如圖1所示，指紋影像處理裝置10包括指紋感測器110、處理器120與記憶體130。其中，指紋感測器110可感測手指的指紋，並據以產生由多個畫素組合而成的一原始影像。此外，指紋感測器110可例如是光學式感測器或是電容式感測器…等。FIG. 1 is a schematic diagram of a fingerprint image processing apparatus according to an embodiment of the invention. As shown in FIG. 1, the fingerprint image processing apparatus 10 includes a fingerprint sensor 110, a processor 120, and a memory 130. The fingerprint sensor 110 can sense the fingerprint of the finger and generate an original image composed of a plurality of pixels. In addition, the fingerprint sensor 110 can be, for example, an optical sensor or a capacitive sensor or the like.
圖2為依據本發明一實施例之指紋影像處理方法的流程圖，以下請同時參照圖1與圖2來看指紋影像處理裝置10的操作。處理器120可透過一前置程序，將指紋感測器110所產生的原始影像轉換成指紋影像。再者，如步驟S210所示，處理器120會利用第一搜尋演算法從指紋影像中擷取出多個第一指紋特徵。其中，指紋影像包括多個影像區塊。第一搜尋演算法可用以分析影像區塊的灰階值分佈，且處理器120可基於第一搜尋演算法的結果，來判別影像區塊是否包括第一指紋特徵。此外，如步驟S220所示，處理器120會對指紋影像執行一反白處理，以取得一反白指紋影像。2 is a flow chart of a fingerprint image processing method according to an embodiment of the present invention. The operation of the fingerprint image processing apparatus 10 will be described below with reference to FIGS. 1 and 2. The processor 120 can convert the original image generated by the fingerprint sensor 110 into a fingerprint image through a pre-program. Moreover, as shown in step S210, the processor 120 uses the first search algorithm to extract a plurality of first fingerprint features from the fingerprint image. The fingerprint image includes a plurality of image blocks. The first search algorithm can be used to analyze the grayscale value distribution of the image block, and the processor 120 can determine whether the image block includes the first fingerprint feature based on the result of the first search algorithm. In addition, as shown in step S220, the processor 120 performs a whitening process on the fingerprint image to obtain a reverse fingerprint image.
如步驟S230所示，處理器120可利用相同的第一搜尋演算法從反白指紋影像中擷取出多個參考特徵。再者，如步驟S240所示，處理器120可參照所述多個參考特徵的座標，從指紋影像中取得多個第二指紋特徵。換言之，處理器120可透過對指紋影像的反白處理，而利用相同的第一搜尋演算法取得指紋影像中不同的第一指紋特徵與第二指紋特徵。藉此，將可降低指紋特徵在擷取上的運算複雜度，從而可增加指紋特徵的擷取速度，並有助於提升指紋影像處理裝置10在使用上的便利性。As shown in step S230, the processor 120 may utilize the same first search algorithm to extract a plurality of reference features from the highlighted fingerprint image. Furthermore, as shown in step S240, the processor 120 may obtain a plurality of second fingerprint features from the fingerprint image by referring to the coordinates of the plurality of reference features. In other words, the processor 120 can obtain different first fingerprint features and second fingerprint features in the fingerprint image by using the same first search algorithm through the reverse processing of the fingerprint image. Thereby, the computational complexity of the fingerprint feature on the capture can be reduced, thereby increasing the capture speed of the fingerprint feature and helping to improve the convenience of the fingerprint image processing device 10 in use.
在應用上，處理器120可利用所述多個第一指紋特徵與所述多個第二指紋特徵，來辨識或是修補指紋影像。舉例來說，在一實施例中，記憶體130內存有至少一預設指紋影像，且該至少一預設指紋影像包括多個預設特徵。處理器120可將所述多個第一指紋特徵與所述多個第二指紋特徵，分別與記憶體130中的所述多個預設特徵進行比對，以判別指紋影像是否匹配預設指紋影像。此外，在另一實施例中，處理器120可將所述多個第一指紋特徵與所述多個第二指紋特徵分別設定為待修補的指紋特徵，進而將指紋影像中的所述多個第一指紋特徵與所述多個第二指紋特徵予以刪除或是修補。In application, the processor 120 may utilize the plurality of first fingerprint features and the plurality of second fingerprint features to identify or repair the fingerprint image. For example, in an embodiment, the memory 130 has at least one preset fingerprint image, and the at least one preset fingerprint image includes a plurality of preset features. The processor 120 may compare the plurality of first fingerprint features and the plurality of second fingerprint features with the plurality of preset features in the memory 130 to determine whether the fingerprint image matches the preset fingerprint. image. In addition, in another embodiment, the processor 120 may separately set the plurality of first fingerprint features and the plurality of second fingerprint features as fingerprint features to be repaired, and further the plurality of fingerprint images. The first fingerprint feature and the plurality of second fingerprint features are deleted or repaired.
圖3為依據本發明另一實施例之指紋影像處理方法的流程圖，以下將參照圖1與圖3進一步地說明，利用第一指紋特徵與第二指紋特徵來辨識指紋影像的操作。FIG. 3 is a flowchart of a method for processing a fingerprint image according to another embodiment of the present invention. The operation of recognizing a fingerprint image by using the first fingerprint feature and the second fingerprint feature will be further described below with reference to FIGS. 1 and 3.
如步驟S310所示，處理器120可透過一前置程序，將指紋感測器110所產生的原始影像轉換成指紋影像，且所述的前置程序包括分割(segmentation)處理、二值化(binarization)處理與細線化(thinning)處理。詳言之，原始影像可分成前景(foreground)與背景(background)，其中指紋的所在區域為前景，且背景則為指紋以外的區域。如步驟S311所示，處理器120可透過前置程序中的分割處理濾除原始影像的背景。As shown in step S310, the processor 120 can convert the original image generated by the fingerprint sensor 110 into a fingerprint image through a pre-program, and the pre-program includes segmentation processing and binarization ( Binarization) processing and thinning processing. In detail, the original image can be divided into a foreground and a background, where the area of the fingerprint is the foreground and the background is the area other than the fingerprint. As shown in step S311, the processor 120 may filter the background of the original image through the segmentation process in the pre-program.
再者，處理器120可將原始影像劃分成多個影像區塊，並計算出每一影像區塊的方向場(orientation field)，進而可估測出指紋的流向。此外，處理器120可參照原始影像的方向場來設定濾波器，並利用濾波器來強化原始影像，進而致使原始影像中指紋的紋路更加地清晰。舉例來說，圖4與圖5分別為依據本發明一實施例之原始影像的部分示意圖。其中，圖4列舉出指紋感測器110所產生的原始影像，且圖5列舉出經由處理器120強化後的原始影像。Moreover, the processor 120 can divide the original image into a plurality of image blocks, and calculate an orientation field of each image block, thereby estimating the flow direction of the fingerprint. In addition, the processor 120 can set the filter with reference to the directional field of the original image, and use the filter to strengthen the original image, thereby making the fingerprint of the original image more clear. For example, FIG. 4 and FIG. 5 are partial schematic views of an original image according to an embodiment of the invention, respectively. 4 shows the original image generated by the fingerprint sensor 110, and FIG. 5 lists the original image enhanced by the processor 120.
再者，處理器120可透過二值化處理與細線化處理，以骨架(skeleton)的方式來呈現指紋。具體而言，如步驟S312所示，處理器120可透過前置程序中的二值化處理，將原始影像轉化成二值化影像。其中，處理器120會以一臨界值比對原始影像中各個畫素的畫素值。此外，處理器120會將畫素值大於臨界值的畫素設定成黑色，並將畫素值不大於臨界值的畫素設定為白色，進而形成二值化影像。Moreover, the processor 120 can present the fingerprint in a skeleton manner through the binarization processing and the thinning processing. Specifically, as shown in step S312, the processor 120 can convert the original image into a binarized image through binarization processing in the pre-program. The processor 120 compares the pixel values of the pixels in the original image with a threshold value. In addition, the processor 120 sets the pixel whose pixel value is greater than the critical value to black, and sets the pixel whose pixel value is not greater than the critical value to white, thereby forming a binarized image.
再者，如步驟S313所示，處理器120可透過細線化處理縮減二值化影像中指紋的寬度，並保持指紋的完整性。具體而言，透過細線化處理，指紋的寬度將縮減成單一畫素的寬度，進而形成指紋影像。舉例來說，圖6為依據本發明一實施例之指紋影像的部分示意圖。如圖6所示，原始影像可透過二值化處理與細線化處理而轉換成圖6中的指紋影像600。Moreover, as shown in step S313, the processor 120 can reduce the width of the fingerprint in the binarized image through the thinning process and maintain the integrity of the fingerprint. Specifically, through the thinning process, the width of the fingerprint is reduced to the width of a single pixel, thereby forming a fingerprint image. For example, FIG. 6 is a partial schematic diagram of a fingerprint image according to an embodiment of the invention. As shown in FIG. 6, the original image can be converted into the fingerprint image 600 in FIG. 6 through binarization processing and thinning processing.
如步驟S320所示，處理器120可利用第一搜尋演算法從指紋影像中擷取出多個第一指紋特徵，且所述多個第一指紋特徵可例如是指紋影像600中的多個端點(ending)，例如：端點610~630。此外，如步驟S330，處理器120可透過反白處理取得一反白指紋影像。舉例來說，圖7為依據本發明一實施例之反白指紋影像的部分示意圖。如圖7所示，處理器120可對指紋影像600執行反白處理，以取得圖7中的反白指紋影像700。再者，如步驟S340所示，處理器120可利用相同的第一搜尋演算法從反白指紋影像700中擷取出多個參考特徵，且所述多個參考特徵可例如是反白指紋影像700中的多個端點，例如：端點710~730。As shown in step S320, the processor 120 may use the first search algorithm to extract a plurality of first fingerprint features from the fingerprint image, and the plurality of first fingerprint features may be, for example, multiple endpoints in the fingerprint image 600. (ending), for example: endpoints 610~630. In addition, in step S330, the processor 120 can obtain a reverse fingerprint image by performing reverse white processing. For example, FIG. 7 is a partial schematic diagram of an inverted white fingerprint image according to an embodiment of the invention. As shown in FIG. 7, the processor 120 can perform a whitening process on the fingerprint image 600 to obtain the highlighted fingerprint image 700 in FIG. Moreover, as shown in step S340, the processor 120 may extract a plurality of reference features from the reverse fingerprint image 700 by using the same first search algorithm, and the plurality of reference features may be, for example, a reverse fingerprint image 700. Multiple endpoints in, for example, endpoints 710~730.
值得注意的是，常見的指紋特徵包括端點與分叉點(bifurcation)。此外，端點與分叉點之間具有一對偶性(duality)或是反轉關係(inverse relationship)。亦即，端點的反轉即為分叉點，且分叉點的反轉即為端點。換言之，端點經由反白處理(inverse process)後將呈現為分叉點。因此，針對指紋影像600與反白指紋影像700中位在同一座標位置的影像區塊來看，反白指紋影像700中的端點將可對應到指紋影像600的分叉點。亦即，處理器120可參照反白指紋影像700中端點的座標，從指紋影像600中取得對應的分叉點。It is worth noting that common fingerprint features include endpoints and bifurcations. In addition, there is a pair of duality or inverse relationship between the endpoint and the bifurcation point. That is, the inversion of the endpoint is the bifurcation point, and the inversion of the bifurcation point is the endpoint. In other words, the endpoint will appear as a bifurcation point after the inverse process. Therefore, for the image block of the fingerprint image 600 and the anti-white fingerprint image 700 at the same coordinate position, the endpoint in the reverse fingerprint image 700 may correspond to the bifurcation point of the fingerprint image 600. That is, the processor 120 can obtain the corresponding bifurcation point from the fingerprint image 600 by referring to the coordinates of the endpoints in the reverse fingerprint image 700.
因此，在操作上，如步驟S350所示，處理器120可參照所述多個參考特徵的座標，從指紋影像中取得多個第二指紋特徵，且所述多個第二指紋特徵可例如是指紋影像中的多個分叉點。舉例來說，處理器120可參照反白指紋影像700中端點710~730的座標，從指紋影像600中取得對應的分叉點640~660。值得一提的是，相較於端點的判斷，分叉點在判斷上的錯誤率較高，因此利用端點的第一搜尋演算法取得指紋影像中的分叉點，將有助於提高指紋特徵在擷取上的精確度。Therefore, in operation, as shown in step S350, the processor 120 may obtain a plurality of second fingerprint features from the fingerprint image by referring to the coordinates of the plurality of reference features, and the plurality of second fingerprint features may be, for example, Multiple bifurcation points in the fingerprint image. For example, the processor 120 can obtain the corresponding bifurcation points 640-660 from the fingerprint image 600 by referring to the coordinates of the endpoints 710-730 in the reverse fingerprint image 700. It is worth mentioning that, compared with the judgment of the endpoint, the bifurcation point has a higher error rate in the judgment. Therefore, using the first search algorithm of the endpoint to obtain the bifurcation point in the fingerprint image will help to improve. The accuracy of the fingerprint feature on the capture.
此外，如步驟S390所示，處理器120可將所述多個第一指紋特徵與所述多個第二指紋特徵，分別與記憶體130中的所述多個預設特徵進行比對，以判別指紋影像是否匹配記憶體130中的預設指紋影像。值得注意的是，處理器120所取得的第一指紋特徵與第二指紋特徵有可能並非是真的指紋特徵，因此處理器120更可透過步驟S360~S380移除部分的第一指紋特徵與部分的第二指紋特徵，以進一步地提升指紋辨識的準確度。In addition, as shown in step S390, the processor 120 may compare the plurality of first fingerprint features and the plurality of second fingerprint features to the plurality of preset features in the memory 130, respectively, to It is determined whether the fingerprint image matches the preset fingerprint image in the memory 130. It should be noted that the first fingerprint feature and the second fingerprint feature obtained by the processor 120 may not be true fingerprint features. Therefore, the processor 120 may further remove part of the first fingerprint feature and part through steps S360-S380. The second fingerprint feature further enhances the accuracy of fingerprint recognition.
詳言之，圖8(a)至圖8(d)分別為依據本發明一實施例之用以說明偽特徵的示意圖。如圖8(a)至圖8(d)所示，常見的偽特徵包括：圖8(a)中的斷脊(break ridge)、圖8(b)中的橋(bridge)、圖8(c)中的短脊(short ridge)以及圖8(d)中的洞(hole)。其中，圖8(a)與圖8(b)中的斷脊與橋之間具有對偶性或是反轉關係，且圖8(c)與圖8(d)中的短脊與洞也具有對偶性或是反轉關係。因此，透過對指紋影像的反白處理，處理器120可利用第二搜尋演算法取得指紋影像中的斷脊與橋，並可利用另一第二搜尋演算法取得指紋影像中的短脊與洞。In detail, FIGS. 8(a) to 8(d) are schematic views for explaining pseudo features, respectively, according to an embodiment of the present invention. As shown in FIGS. 8(a) to 8(d), common pseudo features include: a break ridge in FIG. 8(a), a bridge in FIG. 8(b), and FIG. 8 ( The short ridge in c) and the hole in Figure 8(d). Wherein, the broken ridge and the bridge in Fig. 8(a) and Fig. 8(b) have a duality or an inversion relationship, and the short ridges and holes in Fig. 8(c) and Fig. 8(d) also have Duality or reversal relationship. Therefore, through the reverse processing of the fingerprint image, the processor 120 can obtain the broken ridge and the bridge in the fingerprint image by using the second search algorithm, and can obtain the short ridge and the hole in the fingerprint image by using another second search algorithm. .
舉例來說，如步驟S360所示，在辨識指紋影像之前，處理器120可利用第二搜尋演算法從反白指紋影像中擷取出多個條件特徵(例如，斷脊)。其中，反白指紋影像包括多個影像區塊。第二搜尋演算法可用以分析影像區塊的灰階值分佈，且處理器120可基於第二搜尋演算法的結果，來判別影像區塊是否包括條件特徵(例如，斷脊)。再者，如步驟S370所示，處理器120可利用相同的第二搜尋演算法從指紋影像中擷取出多個偽特徵(例如，斷脊)，並可參照所述多個條件特徵的座標從指紋影像中取得其它的偽特徵(例如，橋)。此外，如步驟S380所示，處理器120可將所述多個第一指紋特徵與所述多個第二指紋特徵，分別與上述多個偽特徵進行比對，以藉此辨識出在所述多個第一指紋特徵與所述多個第二指紋特徵中的偽特徵。再者，處理器120可依據比對結果移除部分的第一指紋特徵與部分的第二指紋特徵，以進一步地提升指紋辨識的準確度。For example, as shown in step S360, before identifying the fingerprint image, the processor 120 may utilize the second search algorithm to extract a plurality of condition features (eg, broken ridges) from the highlighted fingerprint image. The anti-white fingerprint image includes a plurality of image blocks. The second search algorithm can be used to analyze the grayscale value distribution of the image block, and the processor 120 can determine whether the image block includes conditional features (eg, broken ridges) based on the results of the second search algorithm. Furthermore, as shown in step S370, the processor 120 may extract a plurality of pseudo features (eg, broken ridges) from the fingerprint image by using the same second search algorithm, and may refer to the coordinates of the plurality of condition features. Other pseudo features (eg, bridges) are taken in the fingerprint image. In addition, as shown in step S380, the processor 120 may compare the plurality of first fingerprint features and the plurality of second fingerprint features to the plurality of pseudo features, respectively, to thereby identify the a plurality of first fingerprint features and dummy features of the plurality of second fingerprint features. Moreover, the processor 120 may remove a portion of the first fingerprint feature and a portion of the second fingerprint feature according to the comparison result to further improve the accuracy of fingerprint recognition.
綜上所述，本發明是對指紋影像執行反白處理，以取得反白指紋影像。此外，本發明利用從反白指紋影像中所擷取出之參考特徵的座標，從指紋影像中取得對應的指紋特徵。藉此，本發明將可利用相同的搜尋演算法從指紋影像中取得不同的兩指紋特徵。如此一來，將可降低指紋特徵在擷取上的運算複雜度，從而可增加指紋特徵的擷取速度，並有助於提升指紋影像處理裝置在使用上的便利性。In summary, the present invention performs a whitening process on a fingerprint image to obtain a reverse fingerprint image. In addition, the present invention utilizes the coordinates of the reference feature extracted from the reverse fingerprint image to retrieve the corresponding fingerprint feature from the fingerprint image. Thereby, the present invention will be able to obtain different two fingerprint features from the fingerprint image using the same search algorithm. In this way, the computational complexity of the fingerprint feature on the capture can be reduced, thereby increasing the capture speed of the fingerprint feature and helping to improve the convenience of the fingerprint image processing device.
雖然本發明已以實施例揭露如上，然其並非用以限定本發明，任何所屬技術領域中具有通常知識者，在不脫離本發明的精神和範圍內，當可作些許的更動與潤飾，故本發明的保護範圍當視後附的申請專利範圍所界定者為準。Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention, and any one of ordinary skill in the art can make some changes and refinements without departing from the spirit and scope of the present invention. The scope of the invention is defined by the scope of the appended claims.
10‧‧‧指紋影像處理裝置
110‧‧‧指紋感測器
120‧‧‧處理器
130‧‧‧記憶體
S210~S240‧‧‧圖2實施例中的各步驟
S310~S390、S311~S313‧‧‧圖3實施例中的各步驟
600‧‧‧指紋影像
610~630、710~730‧‧‧端點
640~660‧‧‧分叉點
700‧‧‧反白指紋影像10‧‧‧Fingerprint processing device
110‧‧‧Finger sensor
120‧‧‧ processor
130‧‧‧ memory
S210~S240‧‧‧ steps in the embodiment of Fig. 2
S310~S390, S311~S313‧‧‧ steps in the embodiment of Fig. 3
600‧‧‧ Fingerprint image
610~630, 710~730‧‧‧ endpoint
640~660‧‧‧ bifurcation point
700‧‧‧Anti-white fingerprint image
圖1為依據本發明一實施例之指紋影像處理裝置的示意圖。 圖2為依據本發明一實施例之指紋影像處理方法的流程圖。 圖3為依據本發明另一實施例之指紋影像處理方法的流程圖。 圖4與圖5分別為依據本發明一實施例之原始影像的部分示意圖。 圖6為依據本發明一實施例之指紋影像的部分示意圖。 圖7為依據本發明一實施例之反白指紋影像的部分示意圖。 圖8(a)至圖8(d)分別為依據本發明一實施例之用以說明偽特徵的示意圖。FIG. 1 is a schematic diagram of a fingerprint image processing apparatus according to an embodiment of the invention. 2 is a flow chart of a fingerprint image processing method according to an embodiment of the invention. FIG. 3 is a flowchart of a fingerprint image processing method according to another embodiment of the present invention. 4 and 5 are partial schematic views of an original image according to an embodiment of the invention, respectively. FIG. 6 is a partial schematic diagram of a fingerprint image according to an embodiment of the invention. FIG. 7 is a partial schematic diagram of an inverted white fingerprint image according to an embodiment of the invention. 8(a) to 8(d) are schematic views for explaining pseudo features, respectively, according to an embodiment of the present invention.
S210~S240‧‧‧圖2實施例中的各步驟 S210~S240‧‧‧ steps in the embodiment of Fig. 2
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW104136796A TWI615780B (en) | 2015-11-09 | 2015-11-09 | Fingerprint image processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW104136796A TWI615780B (en) | 2015-11-09 | 2015-11-09 | Fingerprint image processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| TW201717104A TW201717104A (en) | 2017-05-16 |
| TWI615780B true TWI615780B (en) | 2018-02-21 |
Family
ID=59366802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| TW104136796A TWI615780B (en) | 2015-11-09 | 2015-11-09 | Fingerprint image processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| TW (1) | TWI615780B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111259691B (en) * | 2018-11-30 | 2024-01-19 | 上海耕岩智能科技有限公司 | Biological characteristic analysis method and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW200535712A (en) * | 2004-04-16 | 2005-11-01 | Wison Technology Corp | Wireless fingerprint recognition system |
| US20100232659A1 (en) * | 2009-03-12 | 2010-09-16 | Harris Corporation | Method for fingerprint template synthesis and fingerprint mosaicing using a point matching algorithm |
| CN102831403A (en) * | 2012-08-10 | 2012-12-19 | 深圳市奔凯安全技术有限公司 | Identification method based on fingerprint feature points |
| CN104615992A (en) * | 2015-02-11 | 2015-05-13 | 浙江中烟工业有限责任公司 | Long-distance fingerprint dynamic authentication method |
| TW201533601A (en) * | 2014-02-28 | 2015-09-01 | Alibaba Group Services Ltd | Method and device for extracting characteristic information |
-
2015
- 2015-11-09 TW TW104136796A patent/TWI615780B/en active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW200535712A (en) * | 2004-04-16 | 2005-11-01 | Wison Technology Corp | Wireless fingerprint recognition system |
| US20100232659A1 (en) * | 2009-03-12 | 2010-09-16 | Harris Corporation | Method for fingerprint template synthesis and fingerprint mosaicing using a point matching algorithm |
| CN102831403A (en) * | 2012-08-10 | 2012-12-19 | 深圳市奔凯安全技术有限公司 | Identification method based on fingerprint feature points |
| TW201533601A (en) * | 2014-02-28 | 2015-09-01 | Alibaba Group Services Ltd | Method and device for extracting characteristic information |
| CN104615992A (en) * | 2015-02-11 | 2015-05-13 | 浙江中烟工业有限责任公司 | Long-distance fingerprint dynamic authentication method |
Also Published As
| Publication number | Publication date |
|---|---|
| TW201717104A (en) | 2017-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10262190B2 (en) | Method, system, and computer program product for recognizing face | |
| US9704015B2 (en) | Fingerprint image processing method and device | |
| JP6123975B2 (en) | Feature amount extraction apparatus and feature amount extraction method | |
| JP4238902B2 (en) | Character noise elimination device, character noise elimination method, character noise elimination program | |
| CN110378351B (en) | Seal identification method and device | |
| JP6338429B2 (en) | Subject detection apparatus, subject detection method, and program | |
| WO2014188446A2 (en) | Method and apparatus for image matching | |
| Jamil et al. | Illumination-invariant ear authentication | |
| JP2018142828A (en) | Deposit detector and deposit detection method | |
| JP2019036030A (en) | Object detection device, object detection method and object detection program | |
| CN113516619B (en) | Product surface flaw identification method based on image processing technology | |
| TWI615780B (en) | Fingerprint image processing method and device | |
| Nguyen et al. | Background removal for improving saliency-based person re-identification | |
| Fang et al. | Towards real-time crack detection using a deep neural network with a Bayesian fusion algorithm | |
| Singh et al. | Fingerprint feature extraction using morphological operations | |
| CN106803053B (en) | Fingerprint image processing method and device | |
| Sisodia et al. | A conglomerate technique for finger print recognition using phone camera captured images | |
| TWI775038B (en) | Method and device for recognizing character and storage medium | |
| JP6580201B2 (en) | Subject detection apparatus, subject detection method, and program | |
| TWI618031B (en) | Edge detection method of image | |
| CN111222116A (en) | Intelligent terminal | |
| CN108694347B (en) | Image processing method and device | |
| CN110659536A (en) | Method, device and system for testing resolution of fingerprint identification equipment and storage medium | |
| JP2004151815A (en) | Method, device and program for extracting specific area, and recording medium recording this program | |
| Nguyen et al. | Robust and real-time deep learning system for checking student attendance |