摘要:
A minute amplitude value emphasis device 2 has Fourier transformation devices 211, 212 which treat a two-dimensional original pictorial image 200 with a Fourier transformation to determine Fourier coefficients in x-axis and y-axis directions. Weight devices 221, 222 emphasize the respective Fourier coefficients in the corresponding directions so as to produce weighted Fourier coefficients. Inverse Fourier transformation devices 231, 232 treat the weighted Fourier coefficients with an inverse Fourier transformation in two directions to determine the corresponding minute amplitude value emphasis data 241, 242. A synthesizing device 250 synthesizes the corresponding minute amplitude value emphasis data 241, 242 to produce a minute amplitude value emphasis image 260. An obscure portion of the two-dimensional original pictorial image 200 is rectified to reproduce a clarified pictorial image.
摘要:
In a license plate information reader device (A) for motor vehicles, a CCD camera (1) is provided to produce video image data (11) involving a license plate obtained by photographing a front and rear portion of a motor vehicle. An A/D converter (3) produces a digital multivalue image data (31) by A/D converting the video image data (11). A license plate extracting device (4) is provided to produce a digital multivalue image data (41) corresponding to an area in which the license plate occupies. A literal region extracting device (5) extracts a literal positional region of a letter sequence of the license plate based on the image obtained from the license plate extracting device (4). A literal recognition device (6) is provided to recognize a letter from a literal image (571) of the literal positional region obtained from the literal region extracting device (5). An image emphasis device is provided to emphasize the literal image (571) of the literal positional region by replacing a part of the literal region extracting device (5) with a filter net which serves as a neural network.
摘要翻译:在用于机动车辆的车牌信息读取装置(A)中,提供CCD摄像机(1),以产生涉及通过拍摄机动车辆的前部和后部获得的车牌的视频图像数据(11)。 A / D转换器(3)通过对视频图像数据(11)进行A / D转换来产生数字多值图像数据(31)。 提供牌照提取装置(4)以产生对应于车牌所占据的区域的数字多值图像数据(41)。 文字区域提取装置(5)基于从车牌提取装置(4)获得的图像,提取车牌的字母序列的文字位置区域。 提供文字识别装置(6)以识别从文字区域提取装置(5)获得的文字位置区域的文字图像(571)中的字母。 提供一种图像强调装置,通过用作为神经网络的滤波器网来替换文字区域提取装置(5)的一部分来强调文字位置区域的文字图像(571)。
摘要:
In a fingerprint scanning device for use in identification, a fingerprint image input device is provided to photoelectronically input a specified fingerprint of an entrant. A monochrome image data of the ridge pattern of the entrant fingerprint is stored as fingerprint image data. A feature extraction device has a calculator which treats the ridge pattern image with one-dimensional group-delay spectrum transform in X- and Y-directions. The feature extraction device has the characteristic of isolating and emphasizing peaks of the individual frequency spectra in the form of differential with respect to a phase component frequency in Fourier transform analysis, and determining group-delay spectra in X- and Y-direction respectively as fingerprint feature portions. A distinction device is provided to collate the entrant feature portion with a registrant feature portion which is registered by the fingerprint image input means so as to identify the entrant with the registrant when X-oriented and Y-oriented group-delay spectra are recognized as being the same between the entrant and the registrant by calculating whether Euclidean distances fall short of a predetermined threshold limit upon collating the individual ridge pattern image.
摘要:
A data processor includes an obtainment part that obtains an image of a person's face, a creation part that creates a face direction map in which face images of the person facing respective directions are arranged, based on the image of the person's face obtained by the obtainment part, and a determination part that determines movement of the person's face, based on the face direction map and a moving image of the person's face obtained by the obtainment part.
摘要:
A hybrid biometric authentication device that includes a plurality of feature extraction portions that respectively extract, from biometric information, a plurality of types of feature information that have mutually distinct properties, a feature combining portion that generates hybrid feature information by combining the plurality of types of feature information, a feature information storage portion that stores the hybrid feature information, a plurality of similarity computation portions that separates each of new information and registered information into the plurality of types of feature information, and compute a plurality of degrees of similarity between separate sets of a same type of the feature information, and a determination portion that, based on the plurality of degrees of similarity, determines whether the biometric information on which the new information is based and the biometric information on which the registered information is based have been acquired from a same person.
摘要:
A defect inspection apparatus for inspecting an object to be inspected for a defect by processing an image taken from the object, includes: neural networks provided respectively for individual defect types to be classified; a learning unit which makes the neural networks learn based on the corresponding defect types to be classified; and a defect detection unit which classifies and detects defect types using the neural networks that have learned.
摘要:
The present invention provides technologies for narrowing down fingerprints images, which will be used for identity determination, without extracting auxiliary information such as a fingerprint pattern, thereby shortening the time required for fingerprint verification. The device according to the present invention includes a storage means 26 for storing characteristic information extracted from fingerprint images of registered persons, and a collection means 10 for collecting a fingerprint image. First, a extraction means 14 extracts characteristic information from the fingerprint image collected by the collection means 10. Next, a narrowing means 16 calculates a similarity between part of the characteristic information of the person to be identified, which was extracted by the extraction means 14, and corresponding part of the characteristic information of each of the registered persons, which is stored in the storage means 26. Based upon the calculated similarity, the registered fingerprints that will be used for the identity determination are narrowed down. Then, an determination means 18 determines whether or not the characteristic information of each of the registered fingerprints, which were narrowed down by the narrowing means 16, matches the characteristic information of the person to be identified, which was extracted by the extraction means 14. According to this device, the registered fingerprints that will be used for the identity determination are narrowed down by using the characteristic information that will be used for the identity determination. Therefore, without extracting auxiliary information, such as a fingerprint pattern, from the collected fingerprint image, the fingerprint images that will be used in order to determine the identity of the fingerprint are narrowed down. Thus, the time required for the fingerprint verification can be shortened.
摘要:
A defect inspection apparatus for inspecting an object to be inspected for a defect by processing an image taken from the object, includes: neural networks provided respectively for individual defect types to be classified; a learning unit which makes the neural networks learn based on the corresponding defect types to be classified; and a defect detection unit which classifies and detects defect types using the neural networks that have learned.
摘要:
A hybrid biometric authentication device that includes a plurality of feature extraction portions that respectively extract, from biometric information, a plurality of types of feature information that have mutually distinct properties, a feature combining portion that generates hybrid feature information by combining the plurality of types of feature information, a feature information storage portion that stores the hybrid feature information, a plurality of similarity computation portions that separates each of new information and registered information into the plurality of types of feature information, and compute a plurality of degrees of similarity between separate sets of a same type of the feature information, and a determination portion that, based on the plurality of degrees of similarity, determines whether the biometric information on which the new information is based and the biometric information on which the registered information is based have been acquired from a same person.
摘要:
A data processor includes an obtainment part that obtains an image of a person's face, a creation part that creates a face direction map in which face images of the person facing respective directions are arranged, based on the image of the person's face obtained by the obtainment part, and a determination part that determines movement of the person's face, based on the face direction map and a moving image of the person's face obtained by the obtainment part.