Abstract: A system for simplified generation of systems for analysis of satellite images to geolocate one or more objects of interest. A plurality of training images labeled for a study object or objects with irrelevant features loaded into a preexisting feature identification subsystem causes automated generation of models for the study object. This model is used to parameterize pre-engineered machine learning elements that are running a preprogrammed machine learning protocol. Training images with the study are used to train object recognition filters. This filter is used to identify the study object in unanalyzed images. The system reports results in a requestor's preferred format.

Abstract: A face recognition method of the present disclosure includes configuring aggregations of feature data that include a plurality of feature data of faces and match to a plurality of personnel data; extracting from an input image a plurality of input feature data that correspond to the feature data and that is equal to or more than a critical value; comparing an aggregation of input feature data that includes the input feature data with each of the pre-stored aggregations of feature data, and selecting from the aggregations of feature data an aggregation of feature data having the greatest similarity with the aggregation of the input feature data; and identifying a person on the image based on personnel data that matches the aggregation of feature data having the greatest similarity.

Abstract: An airborne mine countermeasure system includes a processor coupled to a memory having stored therein software instructions that, when executed by the processor, cause the processor to perform a series of image processing operations. The operations include obtaining input image data from an external image sensor, and extracting a sequence of 2-D slices from the input image data. The operations also include performing a 3-D connected region analysis on the sequence of 2-D slices, and extracting 3-D invariant features in the image data. The operations further include performing coarse filtering, performing fine recognition and outputting an image processing result having an indication of the presence of any mines within the input image data.

Abstract: Provided is a vehicle including a storage unit that stores a vein pattern lookup table including a plurality of reference vein pattern images according to a rotation angle of a driver's hand. The vehicle also includes an image acquisition unit that acquires a driver's image including an image of the driver's hand. The vehicle also includes a controller that extracts a vein pattern image of the driver's hand from the driver's image, authenticates the driver by comparing the vein pattern image with the vein pattern lookup table, and determines a gesture of the driver including at least one of a position of the driver's hand, a direction directed by the driver's hand and a rotation angle of the driver's hand based on the vein pattern image.

Abstract: Techniques and systems are described for performing video segmentation using fully connected object proposals. For example, a number of object proposals for a video sequence are generated. A pruning step can be performed to retain high quality proposals that have sufficient discriminative power. A classifier can be used to provide a rough classification and subsampling of the data to reduce the size of the proposal space, while preserving a large pool of candidate proposals. A final labeling of the candidate proposals can then be determined, such as a foreground or background designation for each object proposal, by solving for a posteriori probability of a fully connected conditional random field, over which an energy function can be defined and minimized.

Abstract: A coding method including dividing pixels of a chrominance component of an input image into blocks having a predetermined size; selecting one among a direct current prediction method, a vertical prediction method, a horizontal prediction method, and a hybrid prediction method according to a user's input; generating a prediction value of each pixel in a current block to be predictively coded, using at least one pixel value among pixel values in an upper reference block adjacent to the current block and in a side reference block adjacent to the current block, according to the selected prediction method; generating a differential value between the prediction value and a corresponding real pixel value in the current block; and coding the differential value and information on the selected prediction method using a predetermined coding method.

Abstract: Methods, systems, computer-readable media, and apparatuses for incremental object detection using a staged process and a band-pass feature extractor are presented. At each stage of the staged process, a different band of features from a plurality of bands of features in image data can be extracted using a dual-threshold local binary pattern operator, and compared with features of a target object within the band for a partial decision. The staged process exits if a rejection decision is made at any stage of the staged process. If no rejection decision is made in each stage of the staged process, the target object is detected. Features extracted at each stage may be from a different image for some applications.

Abstract: Systems, methods, and non-transitory computer-readable media can acquire video content for which video feature descriptors are to be determined. The video content can be processed based at least in part on a convolutional neural network including a set of two-dimensional convolutional layers and a set of three-dimensional convolutional layers. One or more outputs can be generated from the convolutional neural network. A plurality of video feature descriptors for the video content can be determined based at least in part on the one or more outputs from the convolutional neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, to generate a scannable document. In one aspect, a method includes receiving a scan request, wherein the scan request includes a plurality of text images; for each text image of the plurality of text images: rectifying the text image to generate a text image with parallel image lines, generating a plurality of word bounding boxes that enclose one or more connected components in the text image, wherein each word bounding box is associated with a respective word, and generating, for each respective word in the text image, a plurality of points that represent the respective word; combining the plurality of text images to form a single text document; and providing the combined image as a scannable document.

Abstract: Techniques for increasing robustness of a convolutional neural network based on training that uses multiple datasets and multiple tasks are described. For example, a computer system trains the convolutional neural network across multiple datasets and multiple tasks. The convolutional neural network is configured for learning features from images and accordingly generating feature vectors. By using multiple datasets and multiple tasks, the robustness of the convolutional neural network is increased. A feature vector of an image is used to apply an image-related operation to the image. For example, the image is classified, indexed, or objects in the image are tagged based on the feature vector. Because the robustness is increased, the accuracy of the generating feature vectors is also increased. Hence, the overall quality of an image service is enhanced, where the image service relies on the image-related operation.

Abstract: A capacitive fingerprint sensing apparatus including sensing electrodes, a scanning driver, a sensing driver and a processing module is disclosed. In a self-capacitive sensing mode, the scanning driver drives a pair of adjacent scanning lines among the scanning lines and the sensing driver performs self-capacitive sensing through at least one sensing line among the sensing lines to obtain a first fingerprint sensing signal. In a mutual-capacitive sensing mode, the scanning driver drives the pair of adjacent scanning lines and the sensing driver performs mutual-capacitive sensing through at least two adjacent sensing lines among the sensing lines to obtain a second fingerprint sensing signal. The processing module generates a first fingerprint pattern and a second fingerprint pattern according to the first fingerprint sensing signal and the second fingerprint sensing signal and combines the first fingerprint pattern and the second fingerprint pattern into a combined fingerprint pattern.

Abstract: A method for monitoring changes in rangeland includes determining a percent coverage of land cover components in the rangeland, and mapping the land cover components using high resolution imagery. The method further includes linking the mapping to coarser imagery having a larger geographic extent, and interpolating land cover measurements spatially and temporally.

Abstract: Methods and systems for correcting depth irregularities in a three-dimensional scanned model. In particular, one or more embodiments obtain depth data and color data for an object using a depth scanner and a color scanner, respectively. One or more embodiments identify, based on edge information in the color data, regions that have no depth data that are part of the object. One or more embodiments then correct the depth frame by assigning depth data to the identified regions based on a gradient of depth data from areas near the identified regions. The methods and systems use the corrected depth data to generate a corrected three-dimensional model of the object.

Abstract: A lithographic apparatus including an inspection apparatus can measure the overlay error of a target in a scribelane is measured. The overlay error of the required feature in the chip area may differ from this due to, for example, different responses to the exposure process. A model is used to simulate these differences and thus a more accurate measurement of the overlay error of the feature determined.

Abstract: A recognition apparatus according to an embodiment of the present invention includes: a candidate region extraction unit configured to extract a subject candidate region from an image; a feature value extraction unit configured to extract a feature value related to an attribute of the image from the subject candidate region extracted by the candidate region extraction unit; an attribute determination unit configured to determine an attribute of the subject candidate region extracted by the candidate region extraction unit on the basis of the feature value extracted by the feature value extraction unit; and a determination result integration unit configured to identify an attribute of the image by integrating determination results of the attribute determination unit.

Abstract: Various techniques and tools for encoding and decoding (e.g., in a video encoder/decoder) binary information (e.g., skipped macroblock information) are described. In some embodiments, the binary information is arranged in a bit plane, and the bit plane is coded at the picture/frame layer. The encoder and decoder process the binary information and, in some embodiments, switch coding modes. For example, the encoder and decoder use normal, row-skip, column-skip, or differential modes, or other and/or additional modes. In some embodiments, the encoder and decoder define a skipped macroblock as a predicted macroblock whose motion is equal to its causally predicted motion and which has zero residual error. In some embodiments, the encoder and decoder use a raw coding mode to allow for low-latency applications.

Abstract: A system for broad area geospatial object recognition, identification, classification, location and quantification, comprising an image manipulation module to create synthetically-generated images to imitate and augment an existing quantity of orthorectified geospatial images; together with a deep learning module and a convolutional neural network serving as an image analysis module, to analyze a large corpus of orthorectified geospatial images, identify and demarcate a searched object of interest from within the corpus, locate and quantify the identified or classified objects from the corpus of geospatial imagery available to the system. The system reports results in a requestor's preferred format.

Abstract: Patch partition and image processing techniques are described. In one or more implementations, a system includes one or more modules implemented at least partially in hardware. The one or more modules are configured to perform operations including grouping a plurality of patches taken from a plurality of training samples of images into respective ones of a plurality of partitions, calculating an image processing operator for each of the partitions, determining distances between the plurality of partitions that describe image similarity of patches of the plurality of partitions, one to another, and configuring a database to provide the determined distance and the image processing operator to process an image in response to identification of a respective partition that corresponds to a patch taken from the image.

Abstract: A system and method provide object localization in a query image based on a global representation of the image generated with a model derived from a convolutional neural network. Representations of annotated images and a query image are each generated based on activations output by a layer of the model which precedes the fully-connected layers of the neural network. A similarity is computed between the query image representation and each of the annotated image representations to identify a subset of the annotated images having the highest computed similarity. Object location information from at least one of the subset of annotated images is transferred to the query image and information is output, based on the transferred object location information.

Abstract: A method to determine image similarities. The method may include obtaining a first image and a second image and determining a discrete transform difference between a first discrete transform of the first image and a second discrete transform of the second image. The method may also include determining multiple first intensity vectors for the first image and determining multiple second intensity vectors for the second image. The method may also include determining an intensity vector difference between the multiple first intensity vectors and the multiple second intensity vectors and determining a color difference between a first color histogram of the first image and a second color histogram of the second image. The method may also include determining a similarity between the first image and the second image based on the discrete transform difference, the intensity vector difference, and the color difference.