Abstract: An embodiment generally relates to systems and methods for determining cell phone usage automatically by individuals operating vehicles. A processing module can process multi-spectral images or videos of individuals and detect different regions in the image such as face regions, hand regions, and cell phone regions. Further, the processing module can analyze the regions based on locations and numbers of skin pixels and cell phone pixels to determine if the individual is holding his or her cell phone near his or her face. Based on the analysis, it can be determined whether the individual is operating the cell phone. Further, the analysis can yield a confidence level associated with the cell phone usage.

Abstract: Described is a technology for computing visual and textual summaries for tagged image collections. Heterogeneous affinity propagation is used to together identify both visual and textual exemplars. The heterogeneous affinity propagation finds the exemplars for relational heterogeneous data (e.g., images and words) by considering the relationships (e.g., similarities) within pairs of images, pairs of words, and relationships of words to images (affinity) in an integrated manner.

Abstract: Systems and methods for detecting tape on a document are provided. In one embodiment, a method includes capturing a first image of a document. The first image is captured while at least a portion of the document is subjected to a first electromagnetic radiation. The method includes capturing a second image of the document. The second image is captured while at least a portion of the document is subjected to a second electromagnetic radiation. The method also includes comparing the first image to the second image to determine whether tape is adhered to the document.

Abstract: An information processing device includes: a recognizer configured to recognize a predetermined part of a body of a person from an input image including the person; an evaluator configured to evaluate a difference between a recognized input part and a reference part serving as a basis; and a notifying unit configured to notify information relating to the difference of the input part from the reference part based on an evaluation result.

Abstract: Input information of a multidimensional array is divided into a plurality of divided areas, accumulated information is generated by calculating accumulated values at respective element positions of the input information from a corresponding reference location for each of the plurality of divided areas, and the generated accumulated information is held in a memory for each divided area. Calculation using the accumulated information is executed for a predetermined processing range. The input information is divided into the plurality of divided areas so that two neighboring divided areas have an overlapping area, and the overlapping area has a size at least in which the whole processing range fits.

Abstract: A method for searching a database comprising data related to a plurality of fingerprints. Two or more feature points in an image of an unknown fingerprint are identified. A plurality of properties are generated. The plurality of properties are based on the two or more feature points. A number comprising a plurality of digits, e.g. binary digits, is assigned to each of the plurality of properties. In a subsequent step, a numeric representation of said fingerprint is generated based on the assigned numbers. The numeric representation is generated by interleaving the plurality of digits, such that the digits of the numeric representation are arranged in an interleaved or intertwined manner within the numeric representation. The numeric representation is used as a search argument when searching the database. The invention also relates to an apparatus and computer program product.

Abstract: A method for searching a database comprising data related to a plurality of fingerprints. Two or more feature points in an image of an unknown fingerprint are identified. A plurality of properties are generated. The plurality of properties are based on the two or more feature points. A number comprising a plurality of digits, e.g. binary digits, is assigned to each of the plurality of properties. In a subsequent step, a numeric representation of said fingerprint is generated based on the assigned numbers. The numeric representation is generated by interleaving the plurality of digits, such that the digits of the numeric representation are arranged in an interleaved or intertwined manner within the numeric representation. The numeric representation is used as a search argument when searching the database. The invention also relates to an apparatus and computer program product.

Abstract: A method for searching a database comprising data related to a plurality of fingerprints. In step 301, two or more feature points in an image of an unknown fingerprint are identified. A plurality of properties are generated in step 302. The plurality of properties are based on the two or more feature points. In step 303, a number comprising a plurality of digits, e.g. binary digits, is assigned to each of the plurality of properties. In a subsequent step, step 304, a numeric representation of said fingerprint is generated based on the assigned numbers. The numeric representation is generated by interleaving the plurality of digits, such that the digits of the numeric representation are arranged in an interleaved or intertwined manner within the numeric representation. In step 305, the numeric representation is used as a search argument when searching the database. The invention also relates to an apparatus and computer program product.

Abstract: An image processing apparatus includes an image input unit configured to input an image, a scanning unit configured to scan a detection window on the input image, a first discrimination unit configured to determine whether a pattern within the detection window is a subject based on a plurality of characteristic amounts obtained from within a first region among a plurality of regions within the detection window, and a second discrimination unit configured to determine, if it is determined that the pattern is not the subject by the first discrimination unit, whether the pattern is the subject based on a plurality of characteristic amounts obtained from a second region in which a probability that occlusion of the subject occurs is higher than that in the first region among the plurality of regions. Accordingly, a subject can be detected efficiently, and omissions of detection can be reduced.

Abstract: Disclosed is a method of generating image-processing component data which is used when an image of a component to be mounted by a component mounting apparatus is recognized. The method includes extracting first component shape data from CAD data of the component, measuring second component shape data from an image of the component obtained by an imaging device, and generating image-processing component data based on the first and second component shape data.

Abstract: A recognition processing method and an image processing device ends recognition of an object within a predetermined time while maintaining the recognition accuracy. The device extracts combinations of three points defining a triangle whose side length satisfy predetermined criterion values from feature points of the model of a recognition object, registers the extracted combinations as model triangles, and similarly extracts combinations of three points defining a triangle whose side lengths satisfy predetermined criterion values from feature points of the recognition object. The combinations are used as comparison object triangles and associated with the respective model triangles.

Abstract: This disclosure pertains to apparatuses, methods, and computer readable media for red-eye removal techniques using multiple recognition channels. In the following examples, red, golden, and white recognition channels are used. A recognition channel is the monochrome extraction from a color photograph in a manner designed to make one kind of red-eye artifact glow with maximum contrast. Once the red-eye artifact has been characterized by, e.g., size and location, the techniques disclosed herein may then discern whether the red-eye artifact is, for example, a red-, golden-, or white-eye case by examining the configuration and characteristics of prominence bitmasks created for the various recognition channels. Once the type of red-eye case has been discerned, the techniques disclosed herein may then replace the artifact with a photographically reasonable result based on the type of red-eye case being repaired. Specular reflection may also be re-added to the photograph.

Abstract: A system and method are provided to operate upon image data electronically captured with complex spectral content in a plurality of image data pixels within a spatial image plane. A plurality of reference components are provided. A discovery processor is coupled to the general dictionary, and is programmably configured to execute a simultaneous sparse approximation process upon image data pixels of at least a portion of the captured image. The discovery processor discovers therefor a set of core spectral signatures defined in terms of selected reference components from the general dictionary. A match processor programmably configured to execute a selective matching process is also provided for transforming individual image data pixels into linear combinations of selected core spectral signatures. The constituent features of the captured image portion corresponding to the selectively matched core spectral signatures are discriminated according to the linear combination thereof.

Abstract: Method, system and computer program for efficiently extracting and describing scale-space interest points. It is designed towards low overall computational complexity. On one hand, the data acquired during extraction in the description phase is intensively re-used. On the other hand, an algorithmic optimization of the description that dramatically speeds up the process, is proposed. First, the image is filtered with triangle kernel at different scales. The triangle filtered images are reused for extraction of the keypoints dominant orientation and the computation of the DAISY-like descriptor.

Abstract: Various embodiments of the invention provide systems and methods for classifying physical documents that have been converted to digital documents. Specifically, some embodiments are configured to classify digital documents that belong to a document classification whose representative members that lack structure or have varying structure, either of which makes automatic classification of such documents using conventional methods difficult. For example, certain systems and methods according to the invention can be used to classify physical real estate documents that have been converted to digital real estate documents, especially those that lack a discernable document structure.

Abstract: An apparatus includes, a unit generating a sample-texture image, a unit searching a preset-search range for similar pixels and to generate a texture image by assigning a pixel value of each of the similar pixels to a pixel value of a processing-target pixel in the texture image, the preset-search range being included in the sample-texture image and including a position corresponding to a position of the processing-target pixel to which any pixel value is not yet assigned, the similar pixels having, around the similar pixels, variation patterns similar to a pattern of pixels which are located in the texture image near the processing-target pixel and to which pixel values are assigned, and a unit combining the texture image and a base image of a same size as the texture image to obtain a synthetic image, the base image holding shades similar to shades of a transform-target image.

Abstract: Systems and methods for detecting tape on a document are provided. In one embodiment, a method includes capturing a first image of a document. The first image is captured while at least a portion of the document is subjected to a first electromagnetic radiation. The method includes capturing a second image of the document. The second image is captured while at least a portion of the document is subjected to a second electromagnetic radiation. The method also includes comparing the first image to the second image to determine whether tape is adhered to the document.

Abstract: Methods and systems for selecting a representative image of an entity are disclosed. The representative image can be, but is not limited to, that of a person, a corporate logo, other symbol associated with a person or corporation. According to one embodiment, a computer-implemented method for selecting a representative image of an entity is disclosed. The method includes: accessing a collection of images of the entity; clustering, based on similarity of one or more similarity features, images from the collection to form a plurality of similarity clusters; and selecting the representative image from one of said similarity clusters. Further, based on cluster size of said similarity clusters popular clusters can be determined, and the selection of the representative image can be from the popular clusters.

Abstract: Representing a face by jointly quantizing features and spatial location to perform implicit elastic matching between features. A plurality of the features are extracted from a face image and expanded with a corresponding spatial location in the face image. Each of the expanded features is quantized based on one or more randomized decision trees. A histogram of the quantized features is calculated to represent the face image. The histogram is compared to histograms of other face images to identify a match, or to calculate a distance metric representative of a difference between faces.

Abstract: A device is trained for face recognition. A first acquired digital image of a scene includes a face. Face image data is extracted and stored in a face image library along with an unique identifier. A second acquired digital image may or may not include the face of the same person as the face in the first acquired digital image. Face recognition is applied to extracted face data of the second digital image, and the face of the first digital image is displayed as a match to the face of the second digital image when the first and second images are determined to match or the second digital image or a face therein is identified with biometric data stored along with the first digital image when the faces in the first and second images are determined to match.