TW202203088A - Infrared recognition method for human body - Google Patents
Infrared recognition method for human body Download PDFInfo
- Publication number
- TW202203088A TW202203088A TW109123140A TW109123140A TW202203088A TW 202203088 A TW202203088 A TW 202203088A TW 109123140 A TW109123140 A TW 109123140A TW 109123140 A TW109123140 A TW 109123140A TW 202203088 A TW202203088 A TW 202203088A
- Authority
- TW
- Taiwan
- Prior art keywords
- image
- identification
- areas
- target
- human body
- Prior art date
Links
Images
Landscapes
- Image Processing (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
Description
本發明涉及一種人體辨識方法,尤其涉及一種通過紅外線雷射光辨識目標是否為人體的紅外線人體辨識方法。The invention relates to a human body identification method, in particular to an infrared human body identification method for identifying whether a target is a human body through infrared laser light.
現有的人體辨識方法是以一紅外線相機(又稱IR相機)對一人體進行兩次拍攝,以得到不具有近紅外光的一環境光影像(NIR)及具有近紅外光的一紅外光影像(NIRL),接著通過一臉部偵測器(face detection)辨識所述環境光影像及所述紅外光影像中的所述人體臉部位置,接著將所述紅外光影像中的對應所述人體臉部位置的影像資訊取代所述環境光影像中的對應所述人體臉部位置的影像資訊,以產生用以做為辨識影像的一近紅外光微分影像(near-infrared differential; NIRD),通過一分類器將所述近紅外光微分影像中的特徵(反光率)進行分析辨識,以確認所述人體是否為真實人類。The existing human body recognition method uses an infrared camera (also known as an IR camera) to photograph a human body twice to obtain an ambient light image (NIR) without near-infrared light and an infrared light image with near-infrared light ( NIRL), and then identify the position of the human face in the ambient light image and the infrared light image through a face detector, and then identify the human face in the infrared light image corresponding to the human face The image information of the part position replaces the image information corresponding to the position of the human face in the ambient light image, so as to generate a near-infrared differential image (NIRD) used as an identification image, and through a The classifier analyzes and identifies the features (reflectivity) in the near-infrared light differential image to confirm whether the human body is a real human being.
然而,此種方式需要進行兩次拍攝以取得所述環境光影像及所述紅外光影像,方能得到所述近紅外光微分影像進行辨識,但於兩次拍照過程中,所述人體不能有明顯地位移,以避免所述環境光影像及所述紅外光影像中的所述人體的位置差異過大,導致所述臉部偵測器無法辨別所述人體的位置,又或者因人體晃動造成所述近紅外光微分影像具有殘影,造成所述分類器無法確認所述紅外光微分影像中的特徵,而無法分析辨識。However, in this method, two shots are required to obtain the ambient light image and the infrared light image, and then the near-infrared light differential image can be obtained for identification. Displaced significantly to avoid the position difference of the human body in the ambient light image and the infrared light image being too large, causing the face detector to be unable to identify the position of the human body, or causing the human body to shake. The near-infrared light differential image has an afterimage, so that the classifier cannot confirm the features in the infrared light differential image, and cannot analyze and identify.
於是,本發明人認為上述缺陷可改善,乃特潛心研究並配合科學原理的運用,終於提出一種設計合理且有效改善上述缺陷的本發明。Therefore, the inventor believes that the above-mentioned defects can be improved. Nate has devoted himself to research and application of scientific principles, and finally proposes an invention with reasonable design and effective improvement of the above-mentioned defects.
本發明所要解決的技術問題在於,針對現有技術的不足提供一種紅外線人體辨識方法,能有效地改善現有的人體辨識方法所可能產生的缺陷。The technical problem to be solved by the present invention is to provide an infrared human body identification method in view of the deficiencies of the prior art, which can effectively improve the possible defects of the existing human body identification method.
本發明實施例公開一種紅外線人體辨識方法,其包括:實施一照射步驟:通過一紅外線雷射光對一目標照射,使所述目標的外表面形成相互間隔配置的多個雷射圖塊,且所述目標的所述外表面在任兩個所述雷射圖塊之間形成有由一環境光所照射的一環境光區域;實施一擷取步驟:通過一影像資訊擷取裝置於所述目標的外表面上擷取一基礎影像,所述基礎影像具有各別對應多個所述雷射圖塊的多個第一影像資訊及各別對應多個所述環境光區域的多個第二影像資訊;實施一影像模擬步驟:於所述基礎影像中,對應任兩個相鄰的所述環境光區域的所述第二影像資訊以一插值法得出一模擬資訊,所述模擬資訊取代對應兩個所述環境光區域之間的所述雷射圖塊的所述第一影像資訊,以產生模擬所述目標僅受所述環境光照射的一模擬影像;實施一影像分析步驟:將所述基礎影像與所述模擬影像進行比對分析以去除所述環境光的影像資訊,而產生一辨識影像,所述辨識影像具有對應多個所述雷射圖塊於所述目標上的多個反光率資訊;實施一辨認步驟:將所述辨識影像通過一分類器進行辨識;其中,所述分類器通過所述辨識影像中的多個所述反光率資訊進行辨識,以確認所述目標是否為一人體。The embodiment of the present invention discloses an infrared human body identification method, which includes: performing an irradiation step: irradiating a target with an infrared laser light, so that the outer surface of the target forms a plurality of laser blocks arranged at intervals from each other, and the An ambient light area irradiated by an ambient light is formed on the outer surface of the target between any two of the laser blocks; a capturing step is performed: an image information capturing device is used to capture the target at the target. A basic image is captured on the outer surface, the basic image has a plurality of first image information corresponding to a plurality of the laser blocks and a plurality of second image information corresponding to the plurality of the ambient light areas respectively ; Implementing an image simulation step: in the base image, the second image information corresponding to any two adjacent ambient light areas is obtained by an interpolation method to obtain a simulation information, and the simulation information replaces the corresponding two The first image information of the laser blocks between the ambient light areas to generate a simulated image simulating that the target is only illuminated by the ambient light; implementing an image analysis step: converting the The basic image and the simulated image are compared and analyzed to remove the image information of the ambient light, and an identification image is generated, and the identification image has a plurality of reflections on the target corresponding to the plurality of laser blocks implementing a recognition step: identifying the identified image through a classifier; wherein, the classifier identifies through a plurality of the reflectance information in the identified image to confirm whether the target is a a human body.
本發明實施例另外公開一種紅外線人體辨識方法,其包括:實施一照射步驟:通過一紅外線雷射光對一目標照射,使所述目標的外表面形成相互間隔配置的多個雷射圖塊,且所述目標的所述外表面在任兩個所述雷射圖塊之間形成有由一環境光所照射的一環境光區域;實施一擷取步驟:通過一影像資訊擷取裝置於所述目標的外表面上擷取一基礎影像,所述基礎影像具有各別對應多個所述雷射圖塊的多個第一影像資訊及各別對應多個所述環境光區域的多個第二影像資訊;實施一影像分析步驟:分析所述基礎影像中的多個所述第一影像資訊及多個所述第二影像資訊,而產生一辨識影像,所述辨識影像具有多個所述雷射圖塊於所述目標上的多個反光率資訊;實施一辨認步驟:將所述辨識影像通過一分類器進行辨識;其中,所述分類器通過所述辨識影像中的多個所述反光率資訊進行辨識,以確認所述目標是否為一人體。The embodiment of the present invention further discloses an infrared human body identification method, which includes: performing an irradiation step: irradiating a target with an infrared laser light, so that the outer surface of the target forms a plurality of laser blocks arranged at intervals from each other, and An ambient light area irradiated by an ambient light is formed on the outer surface of the target between any two of the laser blocks; a capturing step is performed: an image information capturing device is used to capture the target at the target. A base image is captured on the outer surface of the base image, the base image has a plurality of first image information corresponding to a plurality of the laser blocks and a plurality of second images respectively corresponding to the plurality of the ambient light areas information; implementing an image analysis step: analyzing a plurality of the first image information and a plurality of the second image information in the basic image to generate an identification image, the identification image has a plurality of the lasers A plurality of reflectance information of the image block on the target; implementing an identification step: identifying the identification image through a classifier; wherein, the classifier uses a plurality of the reflectances in the identification image. The information is identified to confirm whether the target is a human body.
綜上所述,本發明實施例所公開的紅外線人體辨識方法,通過所述紅外線雷射光於所述目標上產生彼此間隔的多個所述雷射圖塊的方式,就可以於擷取步驟中獲取有所述紅外線雷射光影像資訊的所述基礎影像;據此,通過直接分析所述基礎影像中的所述第一影像資訊(也就是對應多個所述雷射圖塊的影像資訊),而獲取高準度的所述辨識影像。To sum up, in the infrared human body recognition method disclosed in the embodiment of the present invention, a plurality of the laser image blocks spaced apart from each other are generated on the target by the infrared laser light, which can be used in the capturing step. Acquire the basic image with the infrared laser light image information; accordingly, by directly analyzing the first image information in the basic image (that is, the image information corresponding to a plurality of the laser blocks), And the high-precision identification image is acquired.
再者,本發明實施例所公開的紅外線人體辨識方法,更能通過將所述辨識影像區隔為多個所述辨識區域,並選取對應所述目標的多個所述偵測區域(部分所述辨識區域)的方式,據此,使所述分類器能針對每個所述偵測區域中的影像特徵進行辨識,以避免無法分析辨識的情況。Furthermore, the infrared human body recognition method disclosed in the embodiment of the present invention can further divide the recognition image into a plurality of the recognition areas, and select a plurality of the detection areas (some of the detection areas) corresponding to the target. According to this, the classifier can identify the image features in each of the detection areas, so as to avoid the situation that the identification cannot be analyzed.
為使能更進一步瞭解本發明的特徵及技術內容,請參閱以下有關本發明的詳細說明與圖式,然而所提供的圖式僅用於提供參考與說明,並非用來對本發明加以限制。For a further understanding of the features and technical content of the present invention, please refer to the following detailed descriptions and drawings of the present invention. However, the drawings provided are only for reference and description, and are not intended to limit the present invention.
以下是通過特定的具體實施例來說明本發明所公開有關“紅外線人體辨識方法”的實施方式,本領域技術人員可由本說明書所公開的內容瞭解本發明的優點與效果。本發明可通過其他不同的具體實施例加以施行或應用,本說明書中的各項細節也可基於不同觀點與應用,在不悖離本發明的構思下進行各種修改與變更。另外,本發明的附圖僅為簡單示意說明,並非依實際尺寸的描繪,事先聲明。以下的實施方式將進一步詳細說明本發明的相關技術內容,但所公開的內容並非用以限制本發明的保護範圍。The following is a description of the implementation of the "infrared human body recognition method" disclosed in the present invention through specific specific examples, and those skilled in the art can understand the advantages and effects of the present invention from the content disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and various details in this specification can also be modified and changed based on different viewpoints and applications without departing from the concept of the present invention. In addition, the drawings of the present invention are merely schematic illustrations, and are not drawn according to the actual size, and are stated in advance. The following embodiments will further describe the related technical contents of the present invention in detail, but the disclosed contents are not intended to limit the protection scope of the present invention.
應當可以理解的是,雖然本文中可能會使用到“第一”、“第二”、“第三”等術語來描述各種元件或者信號,但這些元件或者信號不應受這些術語的限制。這些術語主要是用以區分一元件與另一元件,或者一信號與另一信號。另外,本文中所使用的術語“或”,應視實際情況可能包括相關聯的列出項目中的任一個或者多個的組合。It should be understood that although terms such as "first", "second" and "third" may be used herein to describe various elements or signals, these elements or signals should not be limited by these terms. These terms are primarily used to distinguish one element from another element, or a signal from another signal. In addition, the term "or", as used herein, should include any one or a combination of more of the associated listed items, as the case may be.
[第一實施例][First Embodiment]
如圖1至圖8所示,其為本發明的第一實施例,本實施例公開一種紅外線人體辨識方法,且上述紅外線人體辨識方法是通過一次擷取(拍攝)的方式獲取具有環境光及紅外光的影像資訊,以進行人體辨識。換個角度說,通過一次以上擷取以獲取具有環境光及紅外光的影像資訊、或是非通過紅外光及環境光進行人體辨識的方法,則其非為本實施例所指的人體辨識方法。As shown in FIG. 1 to FIG. 8 , which are the first embodiment of the present invention, this embodiment discloses an infrared human body recognition method, and the above infrared human body recognition method is to obtain ambient light and Image information of infrared light for human body recognition. In other words, a method for acquiring image information with ambient light and infrared light through more than one capture, or a method for performing human body identification without using infrared light and ambient light, is not the human body identification method referred to in this embodiment.
所述紅外線人體辨識方法包括有:一照射步驟S110、一擷取步驟S120、一影像模擬步驟S140、一影像分析步驟S150、一選取步驟S160、及一辨認步驟S170。需說明的是,上述多個步驟的其中任一個步驟能夠視設計者的需求而省略或是以合理的變化方式取代。The infrared human body identification method includes: an irradiation step S110, a capture step S120, an image simulation step S140, an image analysis step S150, a selection step S160, and an identification step S170. It should be noted that, any one of the above-mentioned steps can be omitted or replaced by a reasonable change according to the needs of the designer.
實施所述照射步驟S110:通過一紅外線雷射光L對一目標G照射,使所述目標G的外表面形成相互間隔配置的多個雷射圖塊LG,且所述目標G的所述外表面在任兩個所述雷射圖塊LG之間形成有由一環境光E所照射的一環境光區域EA。需說明的是,所述目標G的所述外表面是暴露於所述環境光E之下,也就是說,所述紅外線雷射光L照射於所述目標G的所述外表面時,每個所述雷射圖塊LG的位置也有所述環境光E,而非僅有所述紅外線雷射光L。Carrying out the irradiation step S110 : irradiating a target G with an infrared laser light L, so that the outer surface of the target G forms a plurality of laser blocks LG arranged at intervals, and the outer surface of the target G forms a plurality of laser blocks LG An ambient light area EA illuminated by an ambient light E is formed between any two of the laser blocks LG. It should be noted that the outer surface of the target G is exposed to the ambient light E, that is, when the infrared laser light L is irradiated on the outer surface of the target G, each The location of the laser block LG also has the ambient light E instead of the infrared laser light L alone.
具體來說,由所述紅外線雷射光L所產生的多個所述雷射圖塊LG以縱向條紋狀的方式呈現於所述目標G的所述外表面上,且多個所述雷射圖塊LG的總數量不小於6個,而於任兩個所述雷射圖塊LG之間形成有所述環境光區域EA,所述環境光區域EA是為不被所述紅外線雷射光L所照射的區域,但不受限於本實施例所載。舉例來說,本發明於未繪示的其他實施例中,多個所述雷射圖塊LG能因應設計者的需求進行調整,例如:多個所述雷射圖塊LG也可以是以橫向方式位於所述目標G的所述外表面上,且數量為20個。Specifically, a plurality of the laser image blocks LG generated by the infrared laser light L are presented on the outer surface of the target G in the form of longitudinal stripes, and a plurality of the laser images The total number of blocks LG is not less than 6, and the ambient light area EA is formed between any two of the laser blocks LG, and the ambient light area EA is not affected by the infrared laser light L. The irradiated area is not limited to that set forth in this example. For example, in other embodiments of the present invention that are not shown, the plurality of the laser blocks LG can be adjusted according to the needs of the designer, for example, the plurality of the laser blocks LG can also be in the horizontal direction. The means are located on the outer surface of the target G, and the number is 20.
進一步地說,所述紅外線雷射光L需選用波長為不小於800毫微米(nm),所述紅外線雷射光L於照射人體的皮膚表面(外表面)的反光率大於所述紅外線雷射光L照射非皮膚表面(例如:矽膠)的5%以上;而於本實施例中,所述紅外線雷射光L的波長為840~860毫微米,而所述紅外線雷射光L於照射所述人體的皮膚表面的反光率大於所述紅外線雷射光L照射非皮膚表面的反光率的15%,但不受限於本實施例所載。Further, the wavelength of the infrared laser light L needs to be not less than 800 nanometers (nm), and the reflectivity of the infrared laser light L on the skin surface (outer surface) of the human body is greater than that of the infrared laser light L. More than 5% of the non-skin surface (for example: silicone); and in this embodiment, the wavelength of the infrared laser light L is 840-860 nm, and the infrared laser light L irradiates the skin surface of the human body The reflectivity of the infrared laser light L is greater than 15% of the reflectivity of the non-skin surface irradiated by the infrared laser light L, but is not limited to what is described in this embodiment.
換個方式說,如圖2中的圖表所示,此圖表用以顯示不同波長的所述紅外線雷射光L照射於淺色矽膠表面、深色矽膠表面、淺色皮膚表面、及深色皮膚表面的反射率,此圖表的橫軸為波長(nm),縱軸為反光率(%);需說明的是,深、淺色皮膚表面是用以表示人體不同膚色的皮膚,而深、淺色矽膠表面則是由矽膠或其他類似材質構成不同膚色的假臉。由此圖表可以明顯發現,當所述紅外線雷射光L的波長為840~860毫微米時,照射於深、淺色皮膚表面的反射率明顯不同於照射於深、淺色矽膠表面的反射率。In other words, as shown in the graph in FIG. 2 , this graph is used to show that the infrared laser light L of different wavelengths irradiates the light-colored silica gel surface, the dark-colored silica gel surface, the light-colored skin surface, and the dark-colored skin surface. Reflectance, the horizontal axis of this graph is wavelength (nm), and the vertical axis is reflectance (%). The surface is made of silicone or other similar materials to form fake faces of different skin tones. From this chart, it can be clearly found that when the wavelength of the infrared laser light L is 840-860 nm, the reflectance irradiated on the dark and light-colored skin surfaces is significantly different from that on the dark and light-colored silicone surfaces.
實施所述擷取步驟S120:配合圖3所示,通過一影像資訊擷取裝置C於所述目標G的所述外表面上擷取一基礎影像P1,所述基礎影像P1具有各別對應多個所述雷射圖塊LG的多個第一影像資訊P11及各別對應多個所述環境光區域EA的多個第二影像資訊P12。詳細地說,所述目標G的所述外表面是暴露於所述環境光E之下,也就是說,對應每個所述雷射圖塊LG的所述第一影像資訊P11包含有所述紅外線雷射光L及所述環境光E的影像資訊,而每個所述第一影像資訊P11則僅有所述環境光E的影像資訊。需說明的是,所述影像資訊擷取裝置C於本實施例中能發射出所述紅外線雷射光L(如圖1及圖9所示)。Carry out the capturing step S120 : as shown in FIG. 3 , capture a base image P1 on the outer surface of the target G by an image information capturing device C, and the base image P1 has corresponding multiple A plurality of first image information P11 of each of the laser blocks LG and a plurality of second image information P12 corresponding to a plurality of the ambient light areas EA respectively. Specifically, the outer surface of the target G is exposed to the ambient light E, that is, the first image information P11 corresponding to each of the laser blocks LG includes the The image information of the infrared laser light L and the ambient light E, and each of the first image information P11 has only the image information of the ambient light E. It should be noted that, in this embodiment, the image information capturing device C can emit the infrared laser light L (as shown in FIG. 1 and FIG. 9 ).
實施所述影像模擬步驟S140:配合圖4所示,於所述基礎影像P1中,對應任兩個相鄰的所述環境光區域EA的所述第二影像資訊P12以一插值法得出一模擬資訊A,所述模擬資訊A取代對應兩個所述環境光區域EA之間的所述雷射圖塊LG的所述第一影像資訊P11,以產生模擬所述目標G僅受所述環境光E照射的一模擬影像P2;換個角度說,所述模擬影像P2是將所述基礎影像P1中的每個所述第一影像資訊P11移除,接著將任兩個相鄰的所述第二影像資訊P12以內插法(所述插值法)計算出所述模擬資訊A,所述模擬資訊A取代兩個所述第二影像資訊P12之間已經移除的所述第一影像資訊P11。Carrying out the image simulation step S140 : as shown in FIG. 4 , in the base image P1 , the second image information P12 corresponding to any two adjacent ambient light areas EA is obtained by an interpolation method. Simulation information A, the simulation information A replaces the first image information P11 corresponding to the laser block LG between the two ambient light areas EA, so as to generate a simulation of the target G only affected by the environment A simulated image P2 illuminated by light E; in other words, the simulated image P2 removes each of the first image information P11 in the base image P1, and then removes any two adjacent first image information P11. The analog information A is calculated by interpolation (the interpolation method) from the two image information P12, and the analog information A replaces the first image information P11 that has been removed between the two second image information P12.
實施所述影像分析步驟S150:參閱圖5所示,將所述基礎影像P1與所述模擬影像P2進行比對分析以去除所述環境光E的影像資訊(也就是多個所述第二影像資訊P12及多個所述模擬資訊A),而產生一辨識影像P3,所述辨識影像P3具有對應多個所述雷射圖塊LG於所述目標上的多個反光率資訊;詳細地說,所述辨識影像P3是將所述基礎影像P1中的所述環境光E的影像資訊減去所述模擬影像P2中的所述環境光E的影像資訊,使所述辨識影像P3不具有任何所述環境光E的影像資訊,而僅具有多個所述雷射圖塊LG(多個所述第一影像資訊P11)於所述目標G的所述外表面上的反光率。Perform the image analysis step S150 : referring to FIG. 5 , compare and analyze the basic image P1 and the simulated image P2 to remove the image information of the ambient light E (that is, a plurality of the second images The information P12 and a plurality of the simulation information A) are used to generate an identification image P3, and the identification image P3 has a plurality of reflectance information corresponding to the plurality of the laser blocks LG on the target; in detail , the identification image P3 is obtained by subtracting the image information of the ambient light E in the basic image P1 from the image information of the ambient light E in the simulated image P2, so that the identification image P3 does not have any The image information of the ambient light E only has the reflectivity of the plurality of the laser blocks LG (the plurality of the first image information P11 ) on the outer surface of the target G.
實施所述選取步驟S160:配合圖6所示,將所述辨識影像P3區隔為多個辨識區域P31,每個所述辨識區域P31具有多個所述反光率資訊;於多個所述辨識區域P31中,選取對應所述目標G的部分所述辨識區域P31,並各別定義為一偵測區域Y,每個所述偵測區域Y內的多個所述反光率資訊計算得出一反光率均值。The selection step S160 is implemented: as shown in FIG. 6 , the identification image P3 is divided into a plurality of identification areas P31 , and each of the identification areas P31 has a plurality of the reflectivity information; In the area P31, a part of the identification area P31 corresponding to the target G is selected, and is respectively defined as a detection area Y, and a plurality of the reflectivity information in each of the detection areas Y is calculated to obtain a Average reflectance.
具體來說,所述辨識影像P3定義有相互垂直的一第一方向D1與一第二方向D2,多個所述辨識區域P31排列成平行所述第一方向D1的M行與平行所述第二方向D2的N列,M和N各為大於2的正整數;也就是說,多個所述辨識區域P31是以M乘N的矩陣方式配置(棋盤狀)。如圖6所示,於本實施例中,多個所述辨識區域P31是排列成平行所述第一方向D1的5行與平行所述第二方向D2的4列,也就是多個所述辨識區域P31的數量為20個,且其中多個所述偵測區域Y為除了對應所述目標G的眼部以外的多個所述辨識區域P31;詳細地說,於圖6中所示,多個所述辨識區域P31由上而下,由左而右依序定義為一第一辨識區域、一第二辨識區域、一第三辨識區域、…、及一第二十辨識區域,而多個所述偵測區Y域於本實施例中為上述第二辨識區域、第三辨識區域、第四辨識區域、第十二辨識區域、第十三辨識區域、第十四辨識區域、第十七辨識區域、第十八辨識區域、及第十九辨識區域,也就是說,多個所述偵測區域Y為圖6中由上而下的第2列以外且對應所述目標G的多個所述辨識區域P31,但不受限於本實施例所載。Specifically, the identification image P3 defines a first direction D1 and a second direction D2 that are perpendicular to each other, and a plurality of the identification regions P31 are arranged in M rows parallel to the first direction D1 and parallel to the first direction D1. In the N columns of the two directions D2, M and N are positive integers greater than 2; that is, the plurality of identification regions P31 are arranged in an M-by-N matrix (checkerboard shape). As shown in FIG. 6 , in this embodiment, a plurality of the identification regions P31 are arranged in 5 rows parallel to the first direction D1 and 4 columns parallel to the second direction D2, that is, a plurality of the The number of identification areas P31 is 20, and a plurality of the detection areas Y are a plurality of the identification areas P31 except for the eyes corresponding to the target G; in detail, as shown in FIG. 6 , A plurality of the identification areas P31 are sequentially defined as a first identification area, a second identification area, a third identification area, . . . , and a twentieth identification area from top to bottom and left to right, and many In this embodiment, the detection areas Y are the second identification area, the third identification area, the fourth identification area, the twelfth identification area, the thirteenth identification area, the fourteenth identification area, and the tenth identification area. The seventh identification area, the eighteenth identification area, and the nineteenth identification area, that is to say, the plurality of detection areas Y are outside the second column from top to bottom in FIG. 6 and correspond to the target G. The identification regions P31 are not limited to those in this embodiment.
進一步地說,所述辨識影像P3於對應所述目標G由上而下(也就是所述第一方向D1)的中間1/3位置處的多個所述辨識區域P31各別定義為一不偵測區域N,多個所述偵測區域Y不位於多個所述不偵測區域N中。詳細地說,參閱圖7所示,多個所述不偵測區域N位於所述辨識影像P3由上而下的第2列中,但不受限於本實施例所載。舉例來說,本發明於未繪示的其他實施例中,所述辨識影像P3區隔為48個,並且排列成平行所述第一方向D1的6行與平行所述第二方向D2的8列(也就是以6乘8的矩陣方式配置),位於由上而下的第3列及第4列的多個所述辨識區域P31則定義為多個所述不偵測區域N。換個角度說,多個所述不偵測區域N是對應所述目標G(人體)的眼部位置;據此,以避免擷取所述目標G(人體)配戴眼鏡時的反光率資訊。Further, a plurality of the identification regions P31 in the
實施所述辨認步驟S170:將所述辨識影像P3通過一分類器(圖中未示)進行辨識;其中,所述分類器通過每個所述偵測區域Y中的所述反光率均值進行辨識,以判定所述目標G是否為一人體。具體來說,所述分類器於本實施例中為支援向量機(Support Vector Machine;SVM),且所述分類器通過每個所述偵測區域Y中的所述反光率均值進行辨識,以確認多個所述反光率均值中,是否有部分所述反光率均值大於其他所述反光率均值,以進行判定。Carrying out the identifying step S170 : identifying the identifying image P3 through a classifier (not shown in the figure); wherein, the classifier identifies through the mean value of the reflectivity in each of the detection areas Y , to determine whether the target G is a human body. Specifically, the classifier is a Support Vector Machine (SVM) in this embodiment, and the classifier is identified by the mean value of the reflectivity in each of the detection areas Y, so as to It is confirmed whether some of the mean values of reflectivity are larger than the other mean values of reflectivity to make a determination.
為了能使本領域技術人員能更加了解本發明於所述辨認步驟S170時的過程,以下將舉一例進行說明,而此例的所述目標為一個由矽膠所製成的假臉(圖中未示),所述假臉模擬真實臉部五官,並且已經依序實施所述照射步驟S110、所述擷取步驟S120、所述位置確認步驟S130、所述影像模擬步驟S140、所述影像分析步驟S150、及所述選取步驟S160;也就是說,所述假臉將實施所述辨認步驟S170。In order to enable those skilled in the art to better understand the process of the present invention in the identification step S170, an example will be given below, and the target in this example is a fake face made of silicone (not shown in the figure). shown), the fake face simulates the real facial features, and the irradiation step S110, the capture step S120, the position confirmation step S130, the image simulation step S140, and the image analysis step have been performed in sequence. S150, and the selection step S160; that is, the fake face will implement the identification step S170.
所述皮膚表面受所述影像資訊擷取裝置C正面照射時,所述皮膚表面除了對應人體額頭的部位為光滑表面外,所述皮膚表面的其他部位則因無法正對所述影像資訊擷取裝置C而具有角度,使所述紅外線雷射光L照射於所述皮膚表面的所述其他部位時不容易被接收,導致於所述皮膚表面的所述其他部位的反光率較低,且接近於所述假臉的反光率,因此,所述紅外線雷射光L於照射所述皮膚表面時,所述紅外線雷射光L於對應所述皮膚表面的所述額頭位置會具有較強的反光率,而所述皮膚表面的所述其他位置的反光率則較低,也就是說,對應所述皮膚表面的所述額頭的多個所述偵測區域Y具有較高的所述反光率均值,而對應所述皮膚表面的所述其他位置的多個所述偵測區域Y具有較低的所述反光率均值;反觀,所述假臉不管是額頭或是其他部位的反光率都十分相近。When the skin surface is directly irradiated by the image information capture device C, except for the part corresponding to the forehead of the human body, the skin surface is a smooth surface, and other parts of the skin surface cannot face the image information capture directly. The device C has an angle, so that the infrared laser light L is not easily received when it is irradiated on the other parts of the skin surface, resulting in a low reflectivity of the other parts of the skin surface, and is close to The reflectivity of the fake face, therefore, when the infrared laser light L illuminates the skin surface, the infrared laser light L will have a strong reflectivity at the forehead position corresponding to the skin surface, and The reflectivity of the other positions on the skin surface is lower, that is to say, the detection areas Y of the forehead corresponding to the skin surface have a higher mean reflectance value, while the corresponding A plurality of the detection areas Y at the other positions on the skin surface have a lower mean value of the reflectivity; on the contrary, the reflectivity of the fake face is very similar whether it is the forehead or other parts.
換個方式說,如圖8中的圖表所示,此圖表為所述紅外線雷射光L以不同角度照射於所述假臉與皮膚表面時的反射率;其中,橫軸為入射角角度,而縱軸為反射率。由此圖表可明顯得知,所述紅外線雷射光L於不同入射角照射所述皮膚表面時,對應的反光率明顯差異較大,而所述紅外線雷射光L於不同入射角照射所述假臉時,對應的反光率則相對前者(也就是照射於所述皮膚表面的反光率)差異較小。In other words, as shown in the graph in FIG. 8 , this graph is the reflectance when the infrared laser light L is irradiated on the fake face and the skin surface at different angles; wherein, the horizontal axis is the angle of incidence, and the vertical axis The axis is reflectance. From the graph, it can be clearly seen that when the infrared laser light L irradiates the skin surface at different incident angles, the corresponding reflectivity is significantly different, and the infrared laser light L illuminates the fake face at different incident angles. When , the corresponding reflectance is relatively small compared to the former (that is, the reflectance irradiated on the skin surface).
也就是說,當所述紅外線雷射光L以入射角接近0度對所述假臉及所述人體進行照射時,所述皮膚表面的反射率會明顯大於所述假臉的反射率,尤其以額頭位置最為明顯;反之,當所述紅外線雷射光L以入射角接近90度對所述假臉及所述人體進行照射時,所述皮膚表面的反射率會明顯趨近於所述假臉的反射率。據此,通過所述紅外線雷射光L於矽膠表面及皮膚表面的反光率差異,使所述分類器能通過多個所述反光率均值的差異辨別出所述假臉為非真實人體。That is to say, when the infrared laser light L irradiates the fake face and the human body with an incident angle close to 0 degrees, the reflectivity of the skin surface will be significantly greater than that of the fake face, especially if the The position of the forehead is the most obvious; on the contrary, when the infrared laser light L irradiates the fake face and the human body with an incident angle close to 90 degrees, the reflectivity of the skin surface will obviously approach that of the fake face. Reflectivity. Accordingly, through the difference in the reflectivity of the infrared laser light L on the surface of the silicone rubber and the surface of the skin, the classifier can identify the fake face as a non-real human body through the difference in the mean values of the reflectivity.
另外需說明的是,多個所述偵測區域Y不位於所述不偵測區域N就是為了避免當人體佩戴眼鏡時,擷取眼鏡鏡面的高反光率均值,而導致所述分類器發生誤判的情況。In addition, it should be noted that the plurality of the detection areas Y are not located in the non-detection area N is to avoid the high reflectivity average value of the mirror surface of the glasses being captured when the human body wears glasses, which may cause the classifier to make a misjudgment Case.
由上述的說明可以清楚知道,所述紅外線人體辨識方法僅需通過所述照射步驟S110、所述擷取步驟S120、所述影像分析步驟S150、所述選取步驟S160、及所述辨認步驟S170就可以達到精準的人體辨識效果,而所述紅外線人體辨識方法多實施所述影像模擬步驟S140,則可進一步地大幅提升人體辨識準確度。It can be clearly seen from the above description that the infrared human body recognition method only needs to pass the irradiation step S110, the capture step S120, the image analysis step S150, the selection step S160, and the identification step S170. An accurate human body recognition effect can be achieved, and the infrared human body recognition method generally implements the image simulation step S140, which can further greatly improve the human body recognition accuracy.
[第二實施例][Second Embodiment]
本實施例類似於上述第一實施例,兩個實施例的相同處則不再加以贅述,而本實施例相較於上述第一實施例的差異主要在於:於實施所述擷取步驟S120與實施所述影像模擬步驟S140之間,所述紅外線人體辨識方法更包含有實施一位置確認步驟S130。This embodiment is similar to the above-mentioned first embodiment, and the similarities between the two embodiments will not be repeated, and the difference between this embodiment and the above-mentioned first embodiment mainly lies in that: in the implementation of the capturing step S120 and the Before performing the image simulation step S140, the infrared human body recognition method further includes performing a position confirmation step S130.
實施所述位置確認步驟S130:分析所述基礎影像P1,以確認多個所述第一影像資訊P11於所述基礎影像P1中的位置。具體來說,所述基礎影像P1包含有紅、藍、綠光資訊(RGB),並且具有一紅色通道(Channel R)、一藍色通道(Channel B)、及一綠色通道(Channel G),通過所述紅色通道與所述綠色通道對所述紅外線雷射光L的反光差異,以確認多個所述第一影像資訊P11於所述基礎影像P1中的位置,但不受限於本實施例所載。舉例來說,所述基礎影像P1也可以是通過所述紅色通道與所述藍色通道對所述紅外線雷射光L的反光差異,以確認多個所述第一影像資訊P11於所述基礎影像P1中的位置。當然,確認多個所述第一影像資訊P11於所述基礎影像P1中的位置的方式,也可以是通過所述基礎影像P1的特徵形狀或高頻位置以取得多個所述第一影像資訊P11於所述基礎影像P1中的位置。The position confirmation step S130 is performed: analyzing the base image P1 to confirm the positions of the plurality of first image information P11 in the base image P1. Specifically, the base image P1 includes red, blue, and green light information (RGB), and has a red channel (Channel R), a blue channel (Channel B), and a green channel (Channel G), The positions of a plurality of the first image information P11 in the basic image P1 are confirmed by the difference in reflection of the infrared laser light L by the red channel and the green channel, but not limited to this embodiment contained. For example, the base image P1 may also be based on the difference in reflection of the infrared laser light L by the red channel and the blue channel, so as to confirm the plurality of first image information P11 in the base image position in P1. Of course, the method of confirming the positions of the plurality of first image information P11 in the base image P1 may also be to obtain the plurality of first image information through the characteristic shape or high-frequency position of the base image P1 The position of P11 in the base image P1.
[第三實施例][Third Embodiment]
如圖9所示,其為本發明的第三實施例,本實施例類似於上述第二實施例,兩個實施例的相同處則不再加以贅述,而本實施例相較於上述第二實施例的差異主要在於:於實施所述照射步驟S110中,多個所述雷射圖塊LG為方塊狀,且多個所述雷射圖塊LG的數量大於50個,使位於任兩個所述雷射圖塊LG之間的形成有所述環境光區域EA。然而需說明的是,多個所述雷射圖塊LG的數量及形狀能因應設計者的需求進行調整,例如:多個所述雷射圖塊LG也可以是三角狀、菱形狀、或是不規則形狀等。As shown in FIG. 9 , it is a third embodiment of the present invention. This embodiment is similar to the above-mentioned second embodiment, and the similarities between the two embodiments will not be repeated. Compared with the above-mentioned second embodiment, this embodiment The difference between the embodiments is mainly that: in the implementation of the irradiation step S110, the plurality of the laser image blocks LG are in a square shape, and the number of the plurality of the laser image blocks LG is greater than 50, so that the laser image blocks LG are located in any two The ambient light area EA is formed between the laser blocks LG. However, it should be noted that the number and shape of the plurality of laser blocks LG can be adjusted according to the needs of the designer. For example, the plurality of laser blocks LG can also be triangular, diamond, or irregular shapes, etc.
[本發明實施例的技術效果][Technical effects of the embodiments of the present invention]
綜上所述,本發明實施例所公開的紅外線人體辨識方法,通過所述紅外線雷射光L於所述目標G上產生彼此間隔的多個所述雷射圖塊LG的方式,就可以於所述擷取步驟S110中獲取有所述紅外線雷射光L影像資訊的所述基礎影像P1;據此,通過直接分析所述基礎影像P1中的所述第一影像資訊P11(也就是對應多個所述雷射圖塊LG的影像資訊),而獲取高品質的所述辨識影像P3;再者,本發明實施例所公開的紅外線人體辨識方法,更能通過將所述辨識影像P3區隔為多個所述辨識區域P31,並選取對應所述目標G的多個所述偵測區域Y(部分所述辨識區域P31)的方式,據此,使所述分類器能針對每個所述偵測區域Y中的影像特徵進行辨識,以避免無法分析辨識的情況。To sum up, in the infrared human body recognition method disclosed in the embodiment of the present invention, the infrared laser light L generates a plurality of the laser blocks LG spaced apart from each other on the target G, so that the In the capturing step S110, the basic image P1 having the image information of the infrared laser light L is acquired; accordingly, by directly analyzing the first image information P11 in the basic image P1 (that is, corresponding to a plurality of The image information of the laser block LG) is obtained to obtain the high-quality identification image P3; in addition, the infrared human body identification method disclosed in the embodiment of the present invention can further divide the identification image P3 into multiple The identification areas P31 are selected, and a plurality of detection areas Y (part of the identification areas P31 ) corresponding to the target G are selected, so that the classifier can detect each detection area. The image features in the area Y are identified to avoid the situation where the identification cannot be analyzed.
以上所公開的內容僅為本發明的優選可行實施例,並非因此侷限本發明的申請專利範圍,所以凡是運用本發明說明書及圖式內容所做的等效技術變化,均包含於本發明的申請專利範圍內。The content disclosed above is only a preferred feasible embodiment of the present invention, and is not intended to limit the scope of the present invention. Therefore, any equivalent technical changes made by using the contents of the description and drawings of the present invention are included in the application of the present invention. within the scope of the patent.
G:目標 L:紅外線雷射光 LG:雷射圖塊 E:環境光 EA:環境光區域 P1:基礎影像 P11:第一影像資訊 P12:第二影像資訊 P2:模擬影像 A:模擬資訊 P3:辨識影像 P31:辨識區域 D1:第一方向 D2:第二方向 Y:偵測區域 N:不偵測區域 C:影像資訊擷取裝置G: target L: Infrared laser light LG: Laser Tiles E: ambient light EA: Ambient Light Area P1: Base Image P11: First Image Information P12: Second image information P2: Simulated image A: Simulation information P3: Identifying images P31: Identification area D1: first direction D2: Second direction Y: Detection area N: No detection area C: Image information capture device
圖1為本發明第一實施例的紅外線人體辨識方法於實施照射步驟的狀態示意圖。FIG. 1 is a schematic diagram of the state of the infrared human body recognition method in the implementation of the irradiation step according to the first embodiment of the present invention.
圖2為本發明第一實施例的紅外線人體辨識方法的紅外線雷射光以不同波段對矽膠表面及皮膚表面照射時的反光率參照圖表。FIG. 2 is a reference chart of the reflectivity of the infrared body recognition method of the first embodiment of the present invention when the infrared laser light irradiates the silicone surface and the skin surface with different wavelength bands.
圖3為本發明第一實施例的紅外線人體辨識方法的基礎影像的平面示意圖。3 is a schematic plan view of a basic image of the infrared human body recognition method according to the first embodiment of the present invention.
圖4為本發明第一實施例的紅外線人體辨識方法的模擬影像的平面示意圖。4 is a schematic plan view of a simulated image of the infrared human body recognition method according to the first embodiment of the present invention.
圖5為本發明第一實施例的紅外線人體辨識方法的辨識影像的平面示意圖。FIG. 5 is a schematic plan view of a recognized image of the infrared human body recognition method according to the first embodiment of the present invention.
圖6為本發明第一實施例的紅外線人體辨識方法的多個辨識影像區隔為多個辨識區域時的平面示意圖。6 is a schematic plan view of the infrared human body recognition method according to the first embodiment of the present invention when a plurality of recognition images are divided into a plurality of recognition areas.
圖7為本發明第一實施例的紅外線人體辨識方法的多個辨識影像中的不偵測區域的平面示意圖。7 is a schematic plan view of a non-detection area in a plurality of identification images of the infrared human body identification method according to the first embodiment of the present invention.
圖8為本發明第一實施例的紅外線人體辨識方法的紅外線雷射光各波段照射於矽膠表面與皮膚表面時的反光率參照圖表。FIG. 8 is a reference chart of the reflectivity of each wavelength band of the infrared laser light irradiated on the silicone surface and the skin surface according to the infrared human body identification method according to the first embodiment of the present invention.
圖9為本發明第三實施例的紅外線人體辨識方法於實施照射步驟的狀態示意圖。FIG. 9 is a schematic diagram of the state of the infrared human body recognition method in the implementation of the irradiation step according to the third embodiment of the present invention.
G:目標G: target
L:紅外線雷射光L: Infrared laser light
LG:雷射圖塊LG: Laser Tiles
E:環境光E: ambient light
EA:環境光區域EA: Ambient Light Area
C:影像資訊擷取裝置C: Image information capture device
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109123140A TWI790459B (en) | 2020-07-09 | 2020-07-09 | Infrared recognition method for human body |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109123140A TWI790459B (en) | 2020-07-09 | 2020-07-09 | Infrared recognition method for human body |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202203088A true TW202203088A (en) | 2022-01-16 |
TWI790459B TWI790459B (en) | 2023-01-21 |
Family
ID=80787652
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW109123140A TWI790459B (en) | 2020-07-09 | 2020-07-09 | Infrared recognition method for human body |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI790459B (en) |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013532366A (en) * | 2010-07-09 | 2013-08-15 | アルダン アサノビッチ サパカリエフ | Mass spectrometry and apparatus thereof |
CN102622588B (en) * | 2012-03-08 | 2013-10-09 | 无锡中科奥森科技有限公司 | Dual-certification face anti-counterfeit method and device |
CN105574518B (en) * | 2016-01-25 | 2020-02-21 | 北京眼神智能科技有限公司 | Method and device for detecting living human face |
GB201709199D0 (en) * | 2017-06-09 | 2017-07-26 | Delamont Dean Lindsay | IR mixed reality and augmented reality gaming system |
TWI712005B (en) * | 2018-05-22 | 2020-12-01 | 呂官諭 | Multi-spectrum high-precision object identification method |
-
2020
- 2020-07-09 TW TW109123140A patent/TWI790459B/en active
Also Published As
Publication number | Publication date |
---|---|
TWI790459B (en) | 2023-01-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10606031B2 (en) | Imaging apparatus, imaging system that includes imaging apparatus, electron mirror system that includes imaging apparatus, and ranging apparatus that includes imaging apparatus | |
US11480816B2 (en) | Computer-implemented method for determining centration parameters | |
KR20190021390A (en) | Method for concealing an object in an image or video and associated augmented reality method | |
US10441168B2 (en) | Computer-implemented method for detecting a corneal vertex | |
Sun et al. | Object surface recovery using a multi-light photometric stereo technique for non-Lambertian surfaces subject to shadows and specularities | |
CN101310161B (en) | Face center position detecting device, face center position detecting method | |
WO2016175234A1 (en) | Color image processing method, color image processing program, and object recognition method and device | |
CN106104630B (en) | Detection apparatus and detection method | |
JP2023503517A (en) | Depth measurement with display | |
CN110520768B (en) | Hyperspectral light field imaging method and system | |
US10650225B2 (en) | Image processing apparatus which determines category to which object in image belongs, method therefor, and object discrimination apparatus | |
US11478145B2 (en) | Multispectral and hyperspectral meibography | |
CA3067555A1 (en) | Device for managing the movements of a robot, and associated treatment robot | |
KR20220134753A (en) | Detector for object recognition | |
KR102645445B1 (en) | 2D skin image analysis system and analysis method using thereof | |
DE112008001530T5 (en) | Contactless multispectral biometric acquisition | |
TWI743875B (en) | Infrared recognition method for human body | |
CN115342927A (en) | Face recognition system and face recognition method | |
TWI790459B (en) | Infrared recognition method for human body | |
KR100974881B1 (en) | Method for rubbing copy with the three-dimension scanning | |
Rantoson et al. | 3D reconstruction of transparent objects exploiting surface fluorescence caused by UV irradiation | |
Benalcazar et al. | Iris recognition: comparing visible-light lateral and frontal illumination to NIR frontal illumination | |
EP3574369A1 (en) | Computer-implemented method for determining centring parameters | |
Ahmad et al. | Oto-BaCTM: An Automated Artificial Intelligence (AI) Detector and Counter for Bagworm (Lepidoptera: Psychidae) Census | |
US12029489B1 (en) | Multispectral and hyperspectral meibography |