TWI462028B - Fingerprint identification system and method thereof - Google Patents
Fingerprint identification system and method thereof Download PDFInfo
- Publication number
- TWI462028B TWI462028B TW101144069A TW101144069A TWI462028B TW I462028 B TWI462028 B TW I462028B TW 101144069 A TW101144069 A TW 101144069A TW 101144069 A TW101144069 A TW 101144069A TW I462028 B TWI462028 B TW I462028B
- Authority
- TW
- Taiwan
- Prior art keywords
- score
- fingerprint data
- comparison
- fingerprint
- processing module
- Prior art date
Links
Landscapes
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Input (AREA)
Description
本發明是有關於一種指紋辨識系統及其方法，特別是有關於一種藉由訓練基準指紋資料，以優化指紋辨識效率之指紋辨識系統及其方法。The invention relates to a fingerprint identification system and a method thereof, in particular to a fingerprint identification system and a method thereof for optimizing fingerprint identification efficiency by training reference fingerprint data.
隨著科技的演進，門禁系統或認證系統已愈來愈普遍。其中，指紋認證為門禁或認證系統中經常使用之方式。然，現有之指紋認證系統，往往因為建立指紋比對基準時之環境不佳，例如使用者之手指不乾淨或是使用者於建立指紋比對基準時角度調整不良等原因，使其建立之指紋比對基準之特徵點不足，或與使用者實際之指紋圖樣相差甚遠，而使得之後比對指紋之效率不佳。With the evolution of technology, access control systems or authentication systems have become more and more common. Among them, fingerprint authentication is a method often used in access control or authentication systems. However, the existing fingerprint authentication system often has a bad environment due to the establishment of a fingerprint comparison benchmark, such as the user's finger is not clean or the user adjusts the angle of the fingerprint comparison benchmark, and the fingerprint is established. The feature points of the comparison benchmark are insufficient, or are far from the actual fingerprint pattern of the user, so that the efficiency of comparing the fingerprints afterwards is not good.
此外，現有之指紋認證系統，一旦建立之指紋比對基準不佳，其修正方式唯有重建指紋比對基準，其設定步驟較繁複且費時，相當不方便。因此，指紋認證系統於應用上受到極大的限制，此為現行極需克服之一大問題。In addition, the existing fingerprint authentication system, once the established fingerprint comparison benchmark is not good, the modification method only rebuilds the fingerprint comparison benchmark, and the setting steps are complicated and time-consuming, which is quite inconvenient. Therefore, the fingerprint authentication system is greatly limited in application, which is one of the major problems that need to be overcome.
綜觀前所述，本發明之發明人思索並設計一種指紋認證系統及其方法，經多年潛心研究，以針對現有技術之缺失加以改善，進而增進產業上之實施利用。As described above, the inventor of the present invention contemplates and designs a fingerprint authentication system and a method thereof, and after years of painstaking research, improves the lack of the prior art, thereby enhancing the implementation and utilization of the industry.
有鑑於上述習知技術之問題，本發明之目的就是在提供一種指紋辨識系統及其方法，以期解決習知技術之指紋辨識系統比對效率不佳，且無法重建比對基準指紋之問題。In view of the above problems of the prior art, the object of the present invention is to provide a fingerprint identification system and a method thereof, in order to solve the problem that the fingerprint identification system of the prior art is inefficient and cannot reconstruct the reference fingerprint.
根據本發明之目的，提出一種指紋辨識系統，其包含儲存模組、輸入模組、融合模組及處理模組。儲存模組儲存複數個基準指紋資料。輸入模組輸入指紋資料。融合模組將指紋資料與先前輸入之指紋資料進行融合，以對應產生融合指紋資料並儲存於儲存模組。處理模組分別將指紋資料及融合指紋資料與各基準指紋資料進行比對，以產生比對結果，並根據比對結果選擇性地將指紋資料或融合指紋資料取代對應之基準指紋資料。According to the purpose of the present invention, a fingerprint identification system is provided, which comprises a storage module, an input module, a fusion module and a processing module. The storage module stores a plurality of reference fingerprint data. Input module input fingerprint data. The fusion module combines the fingerprint data with the previously input fingerprint data to generate the merged fingerprint data and store it in the storage module. The processing module compares the fingerprint data and the fused fingerprint data with each of the reference fingerprint data to generate a comparison result, and selectively replaces the corresponding fingerprint data with the fingerprint data or the fused fingerprint data according to the comparison result.
較佳地，比對結果可包含處理模組對指紋資料進行比對所產生之第一比對分數，及對融合指紋資料進行比對所產生之第二比對分數，處理模組再將第一比對分數及第二比對分數分別與替換門檻分數進行比對，若僅第一比對分數或第二比對分數超過替換門檻分數時，處理模組則以超過替換門檻分數者所對應之指紋資料或融合指紋資料取代對應之基準指紋資料。Preferably, the comparison result may include a first comparison score generated by the processing module comparing the fingerprint data, and a second comparison score generated by comparing the fusion fingerprint data, and the processing module is further The comparison score and the second comparison score are respectively compared with the replacement threshold score. If only the first comparison score or the second alignment score exceeds the replacement threshold score, the processing module corresponds to the replacement threshold score. The fingerprint data or the fused fingerprint data replaces the corresponding reference fingerprint data.
較佳地，處理模組可更將第一比對分數及第二比對分數分別與基本分數進行比對，若僅第一比對分數或第二比對分數大於基本分數時，處理模組始將第一比對分數或第二比對分數與替換門檻分數進行比對。Preferably, the processing module can compare the first comparison score and the second comparison score with the basic score respectively, and if only the first comparison score or the second alignment score is greater than the basic score, the processing module The first alignment score or the second alignment score is initially compared with the replacement threshold score.
較佳地，當第一比對分數及第二比對分數皆超過基本分數時，處理模組可將指紋資料及融合指紋資料分別所對應比對之基準指紋資料進行分析，以產生分析結果，並根據分析結果選擇性地將指紋資料或融合指紋資料取代對應之基準指紋資料。Preferably, when the first comparison score and the second comparison score both exceed the basic score, the processing module may analyze the reference fingerprint data corresponding to the fingerprint data and the fusion fingerprint data respectively to generate an analysis result. According to the analysis result, the fingerprint data or the fusion fingerprint data is selectively replaced by the corresponding reference fingerprint data.
較佳地，當分析結果為二者進行比對之基準指紋資料不一致時，處理模組可僅將第一比對分數與替換門檻分數進行比對，若第一比對分數大於替換門檻分數時，則以指紋資料取代對應之基準指紋資料。Preferably, when the analysis result is inconsistent with the reference fingerprint data of the two, the processing module may only compare the first comparison score with the replacement threshold score, if the first alignment score is greater than the replacement threshold score. , the fingerprint data is replaced by the fingerprint data.
較佳地，當分析結果為二者進行比對之基準指紋資料一致時，處理模組可將第一比對分數與第二比對分數進行比對，再將分數較高者與替換門檻分數進行比對，若該者之分數大於替換門檻分數，則將該者對應之指紋資料或融合指紋資料取代對應之基準指紋資料。Preferably, when the analysis result is consistent with the reference fingerprint data of the two, the processing module can compare the first comparison score with the second comparison score, and then compare the higher score with the replacement threshold score. For comparison, if the score of the person is greater than the replacement threshold score, the corresponding fingerprint data or the fusion fingerprint data is substituted for the corresponding reference fingerprint data.
較佳地，若第一比對分數與第二比對分數相同時，處理模組將具有較多指紋特徵數之指紋資料或融合指紋資料所對應之第一比對分數或第二比對分數，與替換門檻分數進行比對，若該者之分數大於替換門檻分數，則將該者對應之指紋資料或融合指紋資料取代對應之基準指紋資料。Preferably, if the first comparison score is the same as the second comparison score, the processing module will have a fingerprint data with more fingerprint feature numbers or a first comparison score or a second comparison score corresponding to the fusion fingerprint data. And comparing with the replacement threshold score, if the score of the person is greater than the replacement threshold score, the corresponding fingerprint data or the fusion fingerprint data is substituted for the corresponding reference fingerprint data.
根據本發明之目的，另提出一種指紋辨識方法，其包含下列步驟：經由儲存模組儲存複數個基準指紋資料。通過輸入模組輸入指紋資料。透過融合模組將指紋資料與先前輸入之指紋資料進行融合，以對應產生融合指紋資料並儲存於儲存模組。藉由處理模組分別將指紋資料及融合指紋資料與各基準指紋資料進行比對，以產生比對結果，並根據比對結果選擇性地將指紋資料或融合指紋資料取代對應之基準指紋資料。According to the purpose of the present invention, a fingerprint identification method is further provided, which comprises the steps of: storing a plurality of reference fingerprint data via a storage module. Enter fingerprint data through the input module. The fingerprint data is merged with the previously input fingerprint data through the fusion module to generate the merged fingerprint data and stored in the storage module. The processing module compares the fingerprint data and the fused fingerprint data with each of the reference fingerprint data to generate a comparison result, and selectively replaces the corresponding fingerprint data with the fingerprint data or the fused fingerprint data according to the comparison result.
較佳地，比對結果可包含處理模組對指紋資料進行比對所產生之第一比對分數，及對融合指紋資料進行比對所產生之第二比對分數，指紋辨識方法可更包含下列步驟：經由處理模組再將第一比對分數及第二比對分數分別與替換門檻分數進行比對，若僅第一比對分數或第二比對分數超過替換門檻分數時，處理模組則以超過替換門檻分數者所對應之指紋資料或融合指紋資料取代對應之基準指紋資料。Preferably, the comparison result may include a first comparison score generated by the processing module comparing the fingerprint data, and a second comparison score generated by comparing the fusion fingerprint data, and the fingerprint identification method may further comprise The following steps: comparing the first alignment score and the second alignment score with the replacement threshold score respectively through the processing module, and if only the first comparison score or the second alignment score exceeds the replacement threshold score, the processing module The group replaces the corresponding reference fingerprint data with the fingerprint data or the fusion fingerprint data corresponding to the replacement threshold score.
較佳地，可更包含下列步驟：透過處理模組更將第一比對分數及第二比對分數分別與基本分數進行比對，若僅第一比對分數或第二比對分數大於基本分數時，處理模組始將第一比對分數或第二比對分數與替換門檻分數進行比對。Preferably, the method further includes the step of: comparing the first comparison score and the second comparison score with the basic score through the processing module, respectively, if only the first comparison score or the second alignment score is greater than the basic At the time of the score, the processing module initially compares the first alignment score or the second alignment score with the replacement threshold score.
較佳地，可更包含下列步驟：當第一比對分數及第二比對分數皆超過基本分數時，透過處理模組將指紋資料及融合指紋資料分別所對應比對之基準指紋資料進行分析，以產生分析結果，並根據分析結果選擇性地將指紋資料或融合指紋資料取代對應之基準指紋資料。Preferably, the method further comprises the following steps: when the first comparison score and the second comparison score exceed the basic score, the fingerprint module and the fusion fingerprint data respectively corresponding to the reference fingerprint data are analyzed by the processing module. To generate an analysis result, and selectively replace the corresponding fingerprint data with the fingerprint data or the fusion fingerprint data according to the analysis result.
較佳地，可更包含下列步驟：當分析結果為二者進行比對之基準指紋資料不一致時，處理模組則僅將第一比對分數與替換門檻分數進行比對，若第一比對分數大於替換門檻分數時，則以指紋資料取代對應之基準指紋資料。Preferably, the method further comprises the following steps: when the analysis result is inconsistent with the reference fingerprint data of the two, the processing module compares only the first comparison score with the replacement threshold score, if the first comparison When the score is greater than the replacement threshold score, the corresponding fingerprint data is replaced by the fingerprint data.
較佳地，可更包含下列步驟：當分析結果為二者進行比對之基準指紋資料一致時，經由處理模組將第一比對分數與第二比對分數進行比對，再將分數較高者與替換門檻分數進行比對，若該者之分數大於替換門檻分數，則將該者對應之指紋資料或融合指紋資料取代對應之基準指紋資料。Preferably, the method further includes the following steps: when the analysis result is consistent with the reference fingerprint data of the two, the first comparison score is compared with the second comparison score by the processing module, and then the score is compared. The high person compares with the replacement threshold score. If the score of the person is greater than the replacement threshold score, the corresponding fingerprint data or the fusion fingerprint data is substituted for the corresponding reference fingerprint data.
較佳地，可更包含下列步驟：若第一比對分數與第二比對分數相同時，處理模組將具有較多指紋特徵數之指紋資料或融合指紋資料所對應之第一比對分數或第二比對分數，與替換門檻分數進行比對，若該者之分數大於替換門檻分數，則將該者對應之指紋資料或融合指紋資料取代對應之基準指紋資料。Preferably, the method further comprises the following steps: if the first comparison score is the same as the second comparison score, the processing module will have a fingerprint data with more fingerprint feature numbers or a first comparison score corresponding to the fusion fingerprint data. Or the second comparison score is compared with the replacement threshold score. If the score of the person is greater than the replacement threshold score, the corresponding fingerprint data or the fusion fingerprint data is substituted for the corresponding reference fingerprint data.
承上所述，本發明之指紋辨識系統及其方法可隨著每次比對指紋，訓練更符合使用者實際指紋之基準指紋資料，進而優化比對指紋之效率。As described above, the fingerprint identification system and the method of the present invention can train the reference fingerprint data more in line with the actual fingerprint of the user with each comparison fingerprint, thereby optimizing the efficiency of the comparison fingerprint.
為利貴審查員瞭解本發明之技術特徵、內容與優點及其所能達成之功效，茲將本發明配合附圖，並以實施例之表達形式詳細說明如下，而其中所使用之圖式，其主旨僅為示意及輔助說明書之用，未必為本發明實施後之真實比例與精準配置，故不應就所附之圖式的比例與配置關係解讀、侷限本發明於實際實施上的權利範圍，合先敘明。The technical features, contents, and advantages of the present invention, as well as the advantages thereof, can be understood by the present inventors, and the present invention will be described in detail with reference to the accompanying drawings. The subject matter is only for the purpose of illustration and description. It is not intended to be a true proportion and precise configuration after the implementation of the present invention. Therefore, the scope and configuration relationship of the attached drawings should not be interpreted or limited. First described.
請一併參閱第1圖及第2圖。第1圖係為本發明之指紋辨識系統之方塊圖；第2圖係為本發明之指紋辨識系統及其方法之簡要示意之流程圖。如圖所示，本發明之指紋辨識系統1包含儲存模組11、輸入模組12、融合模組13及處理模組14。如步驟S101至S103所示，於每一次比對時，指紋辨識系統1將由儲存模組11取得基準指紋資料111，使用者亦藉由輸入模組12輸入指紋資料121，此時融合模組13將本次輸入之指紋資料121與先前之融合指紋資料131進行融合，以產生本次之融合指紋資料131，並將其儲存於儲存模組11中。接著如步驟S104至S108所示，處理模組14比對指紋資料121與基準指紋資料111，而產生第一比對分數，以及比對融合指紋資料131與基準指紋資料111，而產生第二比對分數。處理模組14再根據第一比對分數、第二比對分數以及一預設之基本分數與一預設之替換門檻分數之比對結果141，選擇性地將指紋資料121或融合指紋資料131取代對應之基準指紋資料111。Please refer to Figure 1 and Figure 2 together. 1 is a block diagram of a fingerprint identification system of the present invention; and FIG. 2 is a schematic flow chart of a fingerprint identification system and a method thereof according to the present invention. As shown in the figure, the fingerprint identification system 1 of the present invention comprises a storage module 11, an input module 12, a fusion module 13, and a processing module 14. As shown in steps S101 to S103, the fingerprint identification system 1 will obtain the reference fingerprint data 111 from the storage module 11 and the user also inputs the fingerprint data 121 through the input module 12, and the fusion module 13 at this time. The input fingerprint data 121 is merged with the previous fused fingerprint data 131 to generate the current fused fingerprint data 131 and stored in the storage module 11. Then, as shown in steps S104 to S108, the processing module 14 compares the fingerprint data 121 with the reference fingerprint data 111 to generate a first alignment score, and compares the fusion fingerprint data 131 with the reference fingerprint data 111 to generate a second ratio. For the score. The processing module 14 selectively selects the fingerprint data 121 or the fused fingerprint data 131 according to the first comparison score, the second alignment score, and a predetermined base score and a preset replacement threshold score 141. The corresponding reference fingerprint data 111 is replaced.
請參閱第3圖，其係為本發明之指紋辨識系統及其方法之實施例中指紋資料進行融合之示意圖。如圖所示，融合模組將本次輸入之指紋資料與先前之融合指紋資料融合而產生本次之融合指紋資料，其亦作為下次比對時與輸入之指紋資料融合之用。簡單地說，每一次輸入之指紋資料，其將與之前數次輸入所產生之融合指紋資料進行融合，而產生新的融合指紋資料，並且於下次輸入指紋資料時，與其進行融合。Please refer to FIG. 3, which is a schematic diagram of the fusion of fingerprint data in the embodiment of the fingerprint identification system and the method thereof. As shown in the figure, the fusion module combines the fingerprint data input with the previous fusion fingerprint data to generate the current fusion fingerprint data, which is also used as the fusion of the input fingerprint data in the next comparison. Simply put, each time the fingerprint data is input, it will be merged with the fusion fingerprint data generated by the previous input, and a new fusion fingerprint data is generated, and the fingerprint data is merged with it when the fingerprint data is input next time.
於較佳之實施例中，每一次輸入之指紋資料，需由處理模組判斷為品質好的指紋，亦即指紋資料之取樣品質須超過一定之門檻，例如特徵數、取樣亮度超過一預設值，融合模組始將本次取樣之指紋資料與儲存模組中先前之融合指紋資料進行融合，以產生本次之融合指紋資料。In a preferred embodiment, each input fingerprint data needs to be judged by the processing module as a good quality fingerprint, that is, the sampling quality of the fingerprint data must exceed a certain threshold, for example, the number of features and the sampling brightness exceed a preset value. The fusion module begins to fuse the fingerprint data of the sampling with the previous fusion fingerprint data in the storage module to generate the current fusion fingerprint data.
於上述說明中，由於處理模組根據第一比對分數、第二比對分數、基本分數與替換門檻分數之比對結果，選擇性地將指紋資料或融合指紋資料取代對應之基準指紋資料之流程較為複雜，以下將就比對之各種情形分別說明。In the above description, the processing module selectively replaces the corresponding fingerprint data with the fingerprint data or the fusion fingerprint data according to the comparison result of the first comparison score, the second comparison score, the basic score and the replacement threshold score. The process is more complicated, and the following will explain the various situations.
復請參閱第1圖，並同時參閱第4圖，第4圖係為本發明之指紋辨識系統及其方法之詳述示意之第一流程圖。如第4圖之步驟S201所示，處理模組14分別將第一比對分數與基本分數進行比對，以及將第二比對分數與基本分數進行比對，而產生一比對結果141。如步驟S202至S204所示，當第一比對分數及第二比對分數分別與基本分數比對之結果為第一比對分數超過基本分數，且第二比對分數低於基本分數時，處理模組14將比對第一比對分數與替換門檻分數。若第一比對分數超過替換門檻分數，則將指紋資料121取代與其比對之基準指紋資料111。如步驟S205至S207所示，當第一比對分數及第二比對分數分別與基本分數比對之結果為第一比對分數低於基本分數，且第二比對分數超過基本分數時，處理模組14將比對第二比對分數與替換門檻分數。若第二比對分數超過替換門檻分數，則將融合指紋資料131取代與其比對之基準指紋資料111。Please refer to FIG. 1 and refer to FIG. 4 at the same time. FIG. 4 is a first flowchart of a detailed description of the fingerprint identification system and the method thereof. As shown in step S201 of FIG. 4, the processing module 14 compares the first alignment score with the basic score, and compares the second alignment score with the basic score, respectively, to generate a comparison result 141. As shown in steps S202 to S204, when the first comparison score and the second comparison score are respectively compared with the basic score, the first comparison score exceeds the basic score, and the second comparison score is lower than the basic score, The processing module 14 will compare the first alignment score with the replacement threshold score. If the first alignment score exceeds the replacement threshold score, the fingerprint data 121 is substituted for the reference fingerprint data 111 to which it is compared. As shown in steps S205 to S207, when the first comparison score and the second alignment score are respectively compared with the basic score, the first comparison score is lower than the basic score, and the second comparison score exceeds the basic score, The processing module 14 will compare the second alignment score with the replacement threshold score. If the second alignment score exceeds the replacement threshold score, the fused fingerprint data 131 is substituted for the reference fingerprint data 111 that is aligned with it.
順帶一提的是，第一比對分數超過基本分數，即代表本次之指紋比對，指紋資料121與基準指紋資料111比對成功，而第一比對分數超過替換門檻分數，則代表本次之指紋比對，使用者輸入之指紋資料121，其相較於基準指紋資料111，更適於作為下次之比對基準，因此當第一比對分數超過替換門檻分數，則將指紋資料121取代與其比對之基準指紋資料111，以作為下次之比對基準，藉此於每次之指紋比對時，訓練基準指紋資料111。第二比對分數與基本分數以及替換門檻分數之比對所代表的意義，可簡單由上述說明推得，在此不再重複贅述。Incidentally, the first comparison score exceeds the basic score, that is, the fingerprint comparison of the current time, the fingerprint data 121 is successfully matched with the reference fingerprint data 111, and the first comparison score exceeds the replacement threshold score, and the representative score is The second fingerprint comparison, the fingerprint data 121 input by the user is more suitable as the next comparison benchmark than the reference fingerprint data 111, so when the first comparison score exceeds the replacement threshold score, the fingerprint data is obtained. 121 replaces the reference fingerprint data 111 with which it is compared as the next comparison benchmark, thereby training the reference fingerprint data 111 for each fingerprint comparison. The meaning of the ratio of the second comparison score to the basic score and the replacement threshold score can be simply derived from the above description, and the detailed description is not repeated here.
如步驟S208所示，當第一比對分數及第二比對分數分別與基本分數比對之結果為第一比對分數及第二比對分數兩者皆超過基本分數時，處理模組14將指紋資料121及融合指紋資料131分別所對應比對之基準指紋資料111進行分析，而產生一分析結果。如步驟S209至S211所示，當分析結果為二者進行比對之基準指紋資料111不一致時，處理模組14比對第一比對分數與替換門檻分數，若第一比對分數大於替換門檻分數時，則以指紋資料121取代對應之基準指紋資料111。As shown in step S208, when the first comparison score and the second alignment score are respectively compared with the basic score, the first comparison score and the second comparison score both exceed the basic score, the processing module 14 The reference fingerprint data 111 corresponding to the fingerprint data 121 and the fusion fingerprint data 131 are respectively analyzed to generate an analysis result. As shown in steps S209 to S211, when the analysis result is inconsistent with the comparison of the reference fingerprint data 111, the processing module 14 compares the first comparison score with the replacement threshold score, if the first alignment score is greater than the replacement threshold. In the case of a score, the corresponding reference fingerprint data 111 is replaced with the fingerprint data 121.
換句話說，當分析結果為指紋資料121及融合指紋資料131分別所對應比對之基準指紋資料111不一致時，代表雖然指紋資料121及融合指紋資料131皆比對成功，然而與兩者比對之基準指紋資料111卻不相同。指紋資料121必然為使用者本人之指紋，但融合指紋資料131卻有可能於之前之融合過程混雜了另外之使用者之指紋，而導致指紋資料121及融合指紋資料131與不同之基準指紋資料111比對且比對成功。在此情形下，由於融合指紋資料131有可能於之前之融合過程混雜了另外之使用者之指紋，不必考慮是否將融合指紋資料131取代與其比對之基準指紋資料111。此時處理模組14僅需判斷指紋資料121是否可取代基準指紋資料111，亦即第一比對分數是否大於替換門檻分數即可。In other words, when the analysis result is inconsistent with the reference fingerprint data 111 corresponding to the fingerprint data 121 and the fusion fingerprint data 131 respectively, the fingerprint data 121 and the fusion fingerprint data 131 are successfully matched, but the two are compared. The reference fingerprint data 111 is different. The fingerprint data 121 is necessarily the user's fingerprint, but the fusion fingerprint data 131 may be mixed with the fingerprint of another user in the previous fusion process, resulting in the fingerprint data 121 and the fused fingerprint data 131 and the different reference fingerprint data 111. Compare and compare successfully. In this case, since the fused fingerprint data 131 may be mixed with the fingerprint of another user in the previous fusion process, it is not necessary to consider whether the fused fingerprint data 131 is substituted for the reference fingerprint data 111 that is compared thereto. At this time, the processing module 14 only needs to determine whether the fingerprint data 121 can replace the reference fingerprint data 111, that is, whether the first comparison score is greater than the replacement threshold score.
請再進一步參閱第5圖，其係為本發明之指紋辨識系統及其方法之詳述示意之第二流程圖，第5圖之步驟S301係接續第4圖之步驟S209。當分析結果為指紋資料121及融合指紋資料131二者進行比對之基準指紋資料111一致時，如步驟S301所示，處理模組14將第一比對分數與第二比對分數進行比對。接著如步驟S302至S306所示，處理模組14再將分數較高者與替換門檻分數進行比對，若該者之分數大於替換門檻分數，則將該者對應之指紋資料121或融合指紋資料131取代對應之基準指紋資料111。Please refer to FIG. 5, which is a second flowchart of the detailed description of the fingerprint identification system and the method of the present invention. Step S301 of FIG. 5 is followed by step S209 of FIG. When the analysis result is that the fingerprint data 121 and the fusion fingerprint data 131 are matched by the reference fingerprint data 111, the processing module 14 compares the first comparison score with the second comparison score as shown in step S301. . Then, as shown in steps S302 to S306, the processing module 14 compares the higher score with the replacement threshold score. If the score of the person is greater than the replacement threshold score, the fingerprint data 121 or the fusion fingerprint data corresponding to the candidate is obtained. 131 replaces the corresponding reference fingerprint data 111.
簡單地說，由於指紋資料121及融合指紋資料131二者進行比對之基準指紋資料111一致，指紋資料121及融合指紋資料131係為相同使用者之指紋，此時僅需選出二者中較適合作為比對基準者，亦即比對分數較高者，將其與替換門檻分數進行比對，以判斷是否可取代基準指紋資料111作為新的比對基準即可。Briefly, since the fingerprint data 121 and the fused fingerprint data 131 are the same as the reference fingerprint data 111, the fingerprint data 121 and the fused fingerprint data 131 are the fingerprints of the same user, and only the two of them are selected at this time. It is suitable as a comparison benchmark, that is, a comparison score is higher, and it is compared with the replacement threshold score to determine whether the reference fingerprint data 111 can be replaced as a new comparison benchmark.
順帶一提的是，若第一比對分數與第二比對分數相同時，如步驟S307至S311所示，處理模組14將指紋資料121及融合指紋資料131中指紋特徵數較多者，亦即較適合作為比對基準者，與替換門檻分數進行比對，以判斷是否可取代基準指紋資料111作為新的比對基準。Incidentally, if the first comparison score is the same as the second alignment score, as shown in steps S307 to S311, the processing module 14 has more fingerprint features in the fingerprint data 121 and the fusion fingerprint data 131. That is, it is more suitable as a comparison benchmark to compare with the replacement threshold score to determine whether the reference fingerprint data 111 can be replaced as a new comparison benchmark.
請參閱第6圖，其係為本發明之指紋辨識系統及其方法之簡要示意之另一流程圖。如圖所示，本發明之指紋辨識方法適用於一指紋辨識系統，指紋辨識系統包含儲存模組、輸入模組、融合模組及處理模組，指紋辨識方法包含下列步驟：
在步驟S401中，經由儲存模組儲存複數個基準指紋資料。
在步驟S402中，通過輸入模組輸入指紋資料。
在步驟S403中，透過融合模組將指紋資料與先前輸入之指紋資料進行融合，以對應產生融合指紋資料並儲存於儲存模組。
在步驟S404中，藉由處理模組分別將指紋資料及融合指紋資料與各基準指紋資料進行比對，以產生比對結果，並根據比對結果選擇性地將指紋資料或融合指紋資料取代對應之基準指紋資料。Please refer to FIG. 6, which is another flow chart of the fingerprint identification system and the method thereof. As shown in the figure, the fingerprint identification method of the present invention is applicable to a fingerprint identification system. The fingerprint identification system comprises a storage module, an input module, a fusion module and a processing module. The fingerprint identification method comprises the following steps:
In step S401, a plurality of reference fingerprint data are stored via the storage module.
In step S402, fingerprint data is input through the input module.
In step S403, the fingerprint data is merged with the previously input fingerprint data through the fusion module to generate the merged fingerprint data and stored in the storage module.
In step S404, the processing module compares the fingerprint data and the fused fingerprint data with each of the reference fingerprint data to generate a comparison result, and selectively replaces the fingerprint data or the fused fingerprint data according to the comparison result. Base fingerprint data.
簡而言之，本發明之主要精神，係為使用者每次輸入指紋時，皆會產生一融合指紋，而本次輸入之指紋及融合指紋中圖樣品質較佳者，例如特徵數較多者，當其超過一預設之替換門檻時，將取代本次之比對基準，而成為下一次之比對基準。藉此不斷更新融合指紋及比對基準，而訓練比對基準，優化比對效率。In short, the main spirit of the present invention is that each time a user inputs a fingerprint, a fusion fingerprint is generated, and the fingerprint of the input and the fingerprint of the fusion fingerprint are better, for example, the number of features is larger. When it exceeds a preset replacement threshold, it will replace the current benchmark and become the next benchmark. In this way, the fusion fingerprint and the comparison benchmark are continuously updated, and the comparison benchmark is trained to optimize the comparison efficiency.
上述之實施例，可於實際應用時，針對應用環境加以最佳化其判斷條件。因此，本文於此所揭示的實施例之所有觀點，應被視為用以說明本發明，而非用以限制本發明。本發明的範圍應由後附申請專利範圍所界定，並涵蓋其合法均等物，並不限於先前的描述。The above embodiments can optimize the judgment conditions for the application environment in practical applications. Therefore, the opinions of the embodiments disclosed herein are to be considered as illustrative and not restrictive. The scope of the present invention is defined by the scope of the appended claims, and the legal equivalents thereof are not limited to the foregoing description.
1．．．指紋辨識系統1. . . Fingerprint identification system
11．．．儲存模組11. . . Storage module
111．．．基準指紋資料111. . . Reference fingerprint data
12．．．輸入模組12. . . Input module
121．．．指紋資料121. . . Fingerprint data
13．．．融合模組13. . . Fusion module
131．．．融合指紋資料131. . . Fusion fingerprint data
14．．．處理模組14. . . Processing module
141．．．比對結果141. . . Comparison result
S101~S108、S201~211、S301~S311、S401~S404．．．步驟流程S101~S108, S201~211, S301~S311, S401~S404. . . Step flow
第1圖係為本發明之指紋辨識系統之方塊圖。
第2圖係為本發明之指紋辨識系統及其方法之簡要示意之流程圖。
第3圖係為本發明之指紋辨識系統及其方法之實施例中指紋資料進行融合之示意圖。
第4圖係為本發明之指紋辨識系統及其方法之詳述示意之第一流程圖。
第5圖係為本發明之指紋辨識系統及其方法之詳述示意之第二流程圖。
第6圖係為本發明之指紋辨識系統及其方法之簡要示意之另一流程圖。Figure 1 is a block diagram of a fingerprint identification system of the present invention.
2 is a flow chart showing a schematic diagram of a fingerprint identification system and a method thereof.
FIG. 3 is a schematic diagram of the fusion of fingerprint data in the embodiment of the fingerprint identification system and the method thereof.
Figure 4 is a first flow chart showing the detailed description of the fingerprint identification system and the method thereof.
Figure 5 is a second flow chart showing the detailed description of the fingerprint identification system and the method thereof.
Figure 6 is another flow chart showing a schematic representation of the fingerprint identification system and method thereof.
1．．．指紋辨識系統1. . . Fingerprint identification system
11．．．儲存模組11. . . Storage module
111．．．基準指紋資料111. . . Reference fingerprint data
12．．．輸入模組12. . . Input module
121．．．指紋資料121. . . Fingerprint data
13．．．融合模組13. . . Fusion module
131．．．融合指紋資料131. . . Fusion fingerprint data
14．．．處理模組14. . . Processing module
141．．．比對結果141. . . Comparison result
Claims (14)
一儲存模組，係儲存複數個基準指紋資料；
一輸入模組，係輸入一指紋資料；
一融合模組，係將該指紋資料與先前輸入之該指紋資料進行融合，以對應產生一融合指紋資料並儲存於該儲存模組；以及
一處理模組，係分別將該指紋資料及該融合指紋資料與各該基準指紋資料進行比對，以產生一比對結果，並根據該比對結果選擇性地將該指紋資料或該融合指紋資料取代對應之該基準指紋資料。A fingerprint identification system comprising:
a storage module for storing a plurality of reference fingerprint data;
An input module is to input a fingerprint data;
a fusion module that fuses the fingerprint data with the previously input fingerprint data to generate a merged fingerprint data and stores it in the storage module; and a processing module that respectively combines the fingerprint data and the fingerprint data The fingerprint data is compared with each of the reference fingerprint data to generate a comparison result, and the fingerprint data or the fusion fingerprint data is selectively substituted for the corresponding reference fingerprint data according to the comparison result.
經由該儲存模組儲存複數個基準指紋資料；
通過該輸入模組輸入一指紋資料；
透過該融合模組將該指紋資料與先前輸入之該指紋資料進行融合，以對應產生一融合指紋資料並儲存於該儲存模組；以及
藉由該處理模組分別將該指紋資料及該融合指紋資料與各該基準指紋資料進行比對，以產生一比對結果，並根據該比對結果選擇性地將該指紋資料或該融合指紋資料取代對應之該基準指紋資料。A fingerprint identification method is applicable to a fingerprint identification system. The fingerprint identification system comprises a storage module, an input module, a fusion module and a processing module. The method comprises the following steps:
Storing a plurality of reference fingerprint data via the storage module;
Inputting a fingerprint data through the input module;
The fingerprint data is merged with the previously input fingerprint data to generate a merged fingerprint data and stored in the storage module; and the fingerprint data and the fusion fingerprint are respectively processed by the processing module The data is compared with each of the reference fingerprint data to generate a comparison result, and the fingerprint data or the fusion fingerprint data is selectively substituted for the corresponding reference fingerprint data according to the comparison result.
經由該處理模組再將該第一比對分數及該第二比對分數分別與一替換門檻分數進行比對，若僅該第一比對分數或該第二比對分數超過該替換門檻分數時，該處理模組則以超過該替換門檻分數者所對應之該指紋資料或該融合指紋資料取代對應之該基準指紋資料。The fingerprint identification method of claim 8, wherein the comparison result comprises a first comparison score generated by the processing module comparing the fingerprint data, and comparing the fusion fingerprint data. For one of the second alignment scores generated, the method further includes the following steps:
And comparing, by the processing module, the first comparison score and the second alignment score to an alternate threshold score respectively, if only the first alignment score or the second alignment score exceeds the replacement threshold score The processing module replaces the corresponding fingerprint data with the fingerprint data or the fused fingerprint data corresponding to the replacement threshold score.
透過該處理模組更將該第一比對分數及該第二比對分數分別與一基本分數進行比對，若僅該第一比對分數或該第二比對分數大於該基本分數時，該處理模組始將該第一比對分數或該第二比對分數與該替換門檻分數進行比對。The fingerprint identification method described in claim 9 further includes the following steps:
The first comparison score and the second comparison score are respectively compared with a basic score through the processing module, and if only the first comparison score or the second alignment score is greater than the basic score, The processing module begins to compare the first alignment score or the second alignment score with the replacement threshold score.
當該第一比對分數及該第二比對分數皆超過該基本分數時，透過該處理模組將該指紋資料及該融合指紋資料分別所對應比對之該基準指紋資料進行分析，以產生一分析結果，並根據該分析結果選擇性地將該指紋資料或該融合指紋資料取代對應之該基準指紋資料。The fingerprint identification method according to claim 10, further comprising the following steps:
When the first comparison score and the second comparison score both exceed the basic score, the fingerprint data and the fusion fingerprint data respectively corresponding to the reference fingerprint data are analyzed by the processing module to generate And analyzing the result, and selectively replacing the fingerprint data or the fusion fingerprint data with the corresponding reference fingerprint data according to the analysis result.
當該分析結果為二者進行比對之該基準指紋資料係不一致時，該處理模組則僅將該第一比對分數與該替換門檻分數進行比對，若該第一比對分數大於該替換門檻分數時，則以該指紋資料取代對應之該基準指紋資料。The fingerprint identification method described in claim 11 further includes the following steps:
When the analysis result is inconsistent with the comparison of the reference fingerprint data, the processing module compares the first comparison score with the replacement threshold score, if the first alignment score is greater than the When the threshold score is replaced, the corresponding fingerprint data is replaced by the fingerprint data.
當該分析結果為二者進行比對之該基準指紋資料係一致時，經由該處理模組將該第一比對分數與該第二比對分數進行比對，再將分數較高者與該替換門檻分數進行比對，若該者之分數大於該替換門檻分數，則將該者對應之該指紋資料或該融合指紋資料取代對應之該基準指紋資料。The fingerprint identification method described in claim 11 further includes the following steps:
When the analysis result is consistent with the reference fingerprint data of the two, the first comparison score is compared with the second comparison score by the processing module, and the higher score is compared with the The replacement threshold score is compared. If the score of the person is greater than the replacement threshold score, the fingerprint data corresponding to the person or the fusion fingerprint data is substituted for the corresponding reference fingerprint data.
若該第一比對分數與該第二比對分數相同時，該處理模組將具有較多指紋特徵數之該指紋資料或該融合指紋資料所對應之該第一比對分數或該第二比對分數，與該替換門檻分數進行比對，若該者之分數大於該替換門檻分數，則將該者對應之該指紋資料或該融合指紋資料取代對應之該基準指紋資料。For example, the fingerprint identification method described in claim 13 further includes the following steps:
If the first comparison score is the same as the second comparison score, the processing module will have the fingerprint data with a larger number of fingerprint features or the first alignment score corresponding to the fusion fingerprint data or the second The comparison score is compared with the replacement threshold score. If the score of the person is greater than the replacement threshold score, the fingerprint data corresponding to the person or the fusion fingerprint data is substituted for the corresponding reference fingerprint data.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW101144069A TWI462028B (en) | 2012-11-23 | 2012-11-23 | Fingerprint identification system and method thereof |
| CN201310006431.4A CN103839045B (en) | 2012-11-23 | 2013-01-08 | Fingerprint identification system and fingerprint identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW101144069A TWI462028B (en) | 2012-11-23 | 2012-11-23 | Fingerprint identification system and method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| TW201421375A TW201421375A (en) | 2014-06-01 |
| TWI462028B true TWI462028B (en) | 2014-11-21 |
Family
ID=50802524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| TW101144069A TWI462028B (en) | 2012-11-23 | 2012-11-23 | Fingerprint identification system and method thereof |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN103839045B (en) |
| TW (1) | TWI462028B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184241A (en) * | 2015-08-26 | 2015-12-23 | 广东美的暖通设备有限公司 | Air conditioner integrated controller and control method thereof |
| CN108805572A (en) * | 2017-05-04 | 2018-11-13 | 鲁海伟 | Fingerprint is paid |
| CN109543363B (en) * | 2017-09-22 | 2020-07-24 | 神盾股份有限公司 | Electronic device and software updating and registration template generating method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI223209B (en) * | 2002-03-19 | 2004-11-01 | Fujitsu Prime Software Technol | Computer-readable medium recording a hand-written signature authentication program, and hand-written signature authenticating method and apparatus |
| US20060153433A1 (en) * | 2005-01-07 | 2006-07-13 | Lo Peter Z | Dynamic thresholding for a fingerprint matching system |
| US20060210126A1 (en) * | 2005-03-07 | 2006-09-21 | Lg Electronics Inc. | Apparatus and method of fingerprint recognition for a mobile terminal |
| TW201023053A (en) * | 2008-12-12 | 2010-06-16 | Univ Nat Taiwan Science Tech | Multimodal biometric system and score level fusion method thereof |
| CN102254167A (en) * | 2011-08-16 | 2011-11-23 | 杭州晟元芯片技术有限公司 | Method for reducing false reject rate of fingerprint comparison |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060171571A1 (en) * | 2005-02-01 | 2006-08-03 | Chan Michael T | Systems and methods for quality-based fusion of multiple biometrics for authentication |
| CN101231692A (en) * | 2007-12-24 | 2008-07-30 | 浙江金指码科技有限公司 | Learning type intellectual fingerprint identification comparison method adjusted by fingerprint eigenvalue |
| CN101231691A (en) * | 2007-12-24 | 2008-07-30 | 浙江金指码科技有限公司 | Learning type intellectual fingerprint identification comparison method adjusted based on fingerprint data quantity |
| CN102708360A (en) * | 2012-05-09 | 2012-10-03 | 深圳市亚略特生物识别科技有限公司 | Method for generating and automatically updating fingerprint template |
-
2012
- 2012-11-23 TW TW101144069A patent/TWI462028B/en active
-
2013
- 2013-01-08 CN CN201310006431.4A patent/CN103839045B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI223209B (en) * | 2002-03-19 | 2004-11-01 | Fujitsu Prime Software Technol | Computer-readable medium recording a hand-written signature authentication program, and hand-written signature authenticating method and apparatus |
| US20060153433A1 (en) * | 2005-01-07 | 2006-07-13 | Lo Peter Z | Dynamic thresholding for a fingerprint matching system |
| US20060210126A1 (en) * | 2005-03-07 | 2006-09-21 | Lg Electronics Inc. | Apparatus and method of fingerprint recognition for a mobile terminal |
| TW201023053A (en) * | 2008-12-12 | 2010-06-16 | Univ Nat Taiwan Science Tech | Multimodal biometric system and score level fusion method thereof |
| CN102254167A (en) * | 2011-08-16 | 2011-11-23 | 杭州晟元芯片技术有限公司 | Method for reducing false reject rate of fingerprint comparison |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103839045A (en) | 2014-06-04 |
| TW201421375A (en) | 2014-06-01 |
| CN103839045B (en) | 2017-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Robinson et al. | Face recognition: too bias, or not too bias? | |
| JP5012092B2 (en) | Biometric authentication device, biometric authentication program, and combined biometric authentication method | |
| WO2018166116A1 (en) | Car damage recognition method, electronic apparatus and computer-readable storage medium | |
| JP5979451B2 (en) | Verification result display device, verification result display method, program, and recording medium | |
| CN111898538B (en) | Certificate authentication method and device, electronic equipment and storage medium | |
| Bhanu et al. | Multibiometrics for human identification | |
| CN105989268A (en) | Safety access method and system for human-computer identification | |
| US9548865B2 (en) | Token authentication for touch sensitive display devices | |
| TWI462028B (en) | Fingerprint identification system and method thereof | |
| US20150242840A1 (en) | Systems and methods for dynamic biometric configuration compliance control | |
| CN109783482B (en) | Data violation monitoring method and device | |
| CN111401149B (en) | Lightweight video behavior identification method based on long-short-term time domain modeling algorithm | |
| Patra et al. | Cued-click point graphical password using circular tolerance to increase password space and persuasive features | |
| Ye et al. | Face recognition via active annotation and learning | |
| US8977061B2 (en) | Merging face clusters | |
| CN112039972A (en) | Service processing method, device and equipment | |
| Acosta et al. | City safety perception model based on visual content of street images | |
| CN105988991B (en) | A kind of recognition methods, device and the server of the affiliated languages of surname | |
| US10354164B2 (en) | Method for detecting glint | |
| CN113591657B (en) | OCR layout recognition method and device, electronic equipment and medium | |
| WO2022111688A1 (en) | Face liveness detection method and apparatus, and storage medium | |
| Xu et al. | Face album: towards automatic photo management based on person identity on mobile phones | |
| Wu et al. | Two open-source projects for image aesthetic quality assessment | |
| CN113378277B (en) | User verification method for building decoration system based on BIM technology | |
| CN109635074A (en) | A kind of entity relationship analysis method and terminal device based on public feelings information |