Abstract: Disclosed is a defect detection apparatus. The defect detection apparatus includes an angle extractor configured to extract a slope angle of a pattern from an original image in which a plurality of the patterns are formed at periodic intervals, a pattern period extractor configured to extract a pattern period at which the patterns are separated from each other, by using the slope angle, and an image shifter configured to shift the original image by the pattern period in a direction perpendicular to the slope angle to form the shifted image. The present invention shifts an image by using the slope angle and pattern period of the periodic pattern, thus easily extracting a defect of the original image.

Abstract: System and method for geometric correction of OCT data representing a scan obtained by means of optical coherence tomography imaging of a sample. First scan morphological data relating to a morphology of the sample in the scan are obtained. Then reference morphological data relating to a reference morphology of the sample are obtained. For each of one or more scans of OCT data scan morphological data are compared with the reference morphological data to determine a relative geometric transformation of the morphology of the scan with respect to the reference morphology. Corrected scan is generated by performing on the OCT data representing the scan a transform that relates to the determined relative geometric transformation.

Abstract: A system for document searching can include a camera. The system may further include an image capturing module configured to capture a first image of a first portion of a document, a feature recognition module in communication with the image capturing module, the feature recognition module configured to determine a first feature associated with the first image, a search module configured to send search information to a server and receive a first result from a first search of a set of documents that was performed based on one or more search criteria determined based on the first feature associated with the first image, and a search interface configured to present the first result on the device.

Abstract: A collection of photos is organized by arranging a limited number of clusters of the photos on a predefined topology, so that similar photos are placed in the same cluster or a nearby cluster. Similarity is measured in attribute space. The attributes may include automatically recognized facial expression attributes.

Abstract: Systems, methods and computer program products for determining perceptual similarity between independent images are described. The described systems, methods and computer program products use a similarity distance to determine the perceptual similarity between a first image having a first arrangement of pixels and a second image having a second arrangement of pixels. A processor can determine a first image array corresponding to the first arrangement of pixels and a second image array corresponding of the second arrangement of pixels. The processor can generate a first pixel group set based on the first image array and a second pixel group set based on the second image array. A plurality of pixel group pairs can be generated, and each pixel group pair can be associated with a corresponding pixel group pair distortion. The similarity distance between the first image and the second image can be determined based on the plurality of pixel group pair distortions.

Abstract: Systems and methods are disclosed herein for automatically identifying a query object within a visual medium. The technique generally involves receiving as input to a neural network a query object and a visual medium including the query object. The technique also involves generating, by the neural network, representations of the query object and the visual medium defining features of the query object and the visual medium. The technique also involves generating, by the neural network, a heat map using the representations. The heat map identifies a location of pixels corresponding to the query object within the visual medium and is usable to generate an updated visual medium highlighting the query object.

Abstract: A method and apparatus for embedding a data message in a carrier object using steganography. The method provides a secret key and determines an indicator channel from a plurality of color channels in the carrier object, wherein the indicator channel is the color channel in the carrier object that has a maximum number of different pixel values in the carrier object. The method generates a sorted indicator channel value array based on the channel values and the frequency of occurrence of each value of the indicator channel in the carrier object. For each indicator channel value in the sorted indicator channel value array, the method iterates through the carrier object to determine the pixel in the carrier object whose indicator channel value is the same as the current indicator channel value in the sorted indicator channel value array.

Abstract: The present invention includes: an image capturer capturing an image of the sample to be measured; an image acquirer acquiring image data of the sample captured by the image capturer; a pattern searcher performing, on the image data of the sample acquired by the image acquirer, pattern searching process using a pattern image selected based on the sample and identifying a position in the image matching the pattern image; a profile extractor extracting a profile of the sample based on the position in the image identified by the pattern searcher; a calculator calculating a hardness measurement position of the sample based on the profile extracted by the profile extractor; and a measurer executing hardness testing on the sample based on the hardness measurement position calculated by the calculator and measuring the hardness of the sample.

Abstract: A system comprises a picture and metadata captured by a content capture system; a recognizable characteristic datastore configured to store recognizable characteristics of different users; a module configured to identify a time and a location associated with the picture based on the metadata, and to identify one or more potential target systems within a predetermined range of the location at the time; a characteristic recognition module configured to retrieve the recognizable characteristics of one or more potential users associated with the potential target systems, and evaluate whether the picture includes one or more representations of at least one actual target user from the potential users based on the recognizable characteristics of the potential users; a distortion module configured to distort a feature of the representations of the least one actual target user in response to the determination; a communication module configured to communicate the distorted picture to a computer network.

Abstract: Various aspects of a method and device to process one or more multi-channel images are disclosed herein. The method to process one or more multi-channel images is executed within an electronic device. A channel distance value between each channel of a target patch and corresponding channel of one or more neighbor patches of one or more multi-channel images is determined. The determination of the channel distance value is based on channel data in each channel of the one or more multi-channel images. Based on relative signal information in each channel of the target patch, a channel weight for each channel is dynamically determined. Based on the determined channel distance value and the dynamically determined channel weight for each channel, a patch matching score is determined.

Abstract: A fingerprint identification method is provided. The method includes steps as follows: having a finger press on a photoelectronic sensor module; respectively emitting an invisible light beam reflected to a photoelectronic sensor module after passing through the finger and a visible light beam reflected to the photoelectronic sensor module via a surface of the finger; generating, by the photoelectronic sensor module, photocurrent signals based on the visible light beam and the invisible light beam; respectively generating, by an analog/digital converter module, a first digital signal and a second digital signal based on the photocurrent signals; and outputting, by a processor module, the first digital signal as a gray-scale fingerprint image and a second digital signal as a colored fingerprint image. The invention also provides a fingerprint identification device performing the fingerprint identification method.

Abstract: A method of determining eye position information includes identifying an eye area in a facial image; verifying a two-dimensional (2D) feature in the eye area; and performing a determination operation including, determining a three-dimensional (3D) target model based on the 2D feature; and determining 3D position information based on the 3D target model.

Abstract: An image defect detection device that divides an original print image and a print image printed on the basis of the original print image into corresponding regions, acquires an image feature amount of each divided region, extracts a strength of a difference of each divided region between the original print image and the print image, calculates an image defect detection time indicating a time required to detect a defect of each divided region of the print image from the image feature amount and the strength of the difference of each divided region, calculates an expected image defect value indicating a possibility of presence of a defect in each divided region of the print image from the image feature amount and the strength of the difference of each divided region, determines an order of detection of the image defect of the divided region of the print image.

Abstract: A method of decoding an image in which wherein, when a prediction mode is an inter prediction mode, not an intra prediction mode, a size of at least one prediction unit in the coding unit is determined independently from a size of at least one transformation unit in the coding unit.

Abstract: A robot positioning system having a camera, a processing unit and at least a first line laser. The first line laser is arranged to illuminate a space by projecting vertical laser beams within field of view of the camera. The camera is arranged to record a picture of the space illuminated by the vertical laser beams, and the processing unit is arranged to extract, from the recorded picture, image data representing a line formed by the vertical laser beams being reflected against objects located within the space. The processing unit is further arranged to create, from the extracted line, a representation of the illuminated space along the projected laser lines, in respect of which the robot is positioned. Methods of positioning a robot are also provided.

Abstract: Techniques related to geometric camera self-calibration quality assessment.

Abstract: A method for processing a picture is disclosed. The method according to the invention comprises: segmenting the picture into a background layer and at least another layer; selecting a background template of color harmony for the background layer; determining one template of color harmony for each of the at least another layer from the background template of color harmony depending on the distance between the background layer and said at least another layer. processing the picture by mapping the colors of each segmented layer using the corresponding template of color harmony.

Abstract: Methods and systems recognize alphanumeric characters in an image by computing individual representations of every character of an alphabet at every character position within a certain word transcription length. These methods and systems embed the individual representations of each alphabet character in a common vectorial subspace (using a matrix) and embed a received image of an alphanumeric word into the common vectorial subspace (using the matrix). Such methods and systems compute the utility value of the embedded alphabet characters at every one of the character positions with respect to the embedded alphanumeric character image; and compute the best transcription alphabet character of every one of the image characters based on the utility value of each embedded alphabet character at each character position. Such methods and systems then assign the best transcription alphabet character for each of the character positions to produce a recognized alphanumeric word within the received image.

Abstract: The present disclosure, pertaining to the field of terminal technologies, relates to a method and apparatus for recommending contact information. The method may include: determining an age of an owner of a mobile terminal; determining, based on the determined age of the owner and stored contact photos of a plurality of contacts, a candidate contact from the plurality of contacts; and displaying, in response to receiving a share instruction with respect to a designated image, contact information of the determined candidate contact, the designated image being any image in a photo album to be shared. According to the present disclosure, one or more candidate contacts are determined from a plurality of contacts, and upon receipt of a share instruction with respect to a designated image, contact information of the determined candidate contact is displayed. This may improve speed and accuracy of searching for contact information, reduce search time, and enhance image sharing efficiency.

Abstract: Disclosed herein is a method for producing an evolvable tissue model of a patient and, using this model, modelling physical transformations of the tissue (e.g. deformation) of the tissue model by interacting the tissue model with influence models which model interactions with the tissue such as surgical instruments, pressure, swelling, temperature changes etc. The model is produced from a set of input data of the tissue which includes directional information of the tissue. The directional information is used to produce an oriented tissue map. A tissue model is then produced from the oriented tissue map such that the tissue model reflects the directionality of the tissue component. When the tissue model is subjected to an influence that causes tissue deformation over a period of time, the tissue model directionally deforms over the period of time in a manner which reflects a trajectory of the influence interacting with the directionality of the tissue component.