Sony Corporation

Agilent Technologies, Inc.

Avago Technologies Ecbu IP (singapore) Pte. Ltd.

Daniel A Usikov

Mohammad Gharavi-Alkhansari

Julie Elizabeth Fouquet

John Stewart Wenstrand

Richard Earl Haven

Alexander Berestov

Lee Alton Barford

Golnaz Abdollahian

Hiroyuki Takeda

Nicholas Tufillaro

Wei Ji

Jonathan Qiang Li

Linda Argon Kamas

Various aspects of an image-processing apparatus and method for object boundary stabilization in an image of a sequence of image frames are disclosed. The image-processing apparatus includes an image processor that receives a depth image of a scene from a first-type of sensor and a color image of the scene from the second-type of sensor. The scene may comprise at least an object-of-interest. A first object mask of the object-of-interest is generated by a depth thresholding operation on the received depth image. Dangling-pixels artifact present on a first object boundary of the first object mask, are removed. The first object boundary is smoothened using a moving-template filter on the color image. A second object mask having a second object boundary is generated based on the smoothening of the first object boundary. The object-of-interest from the color image is extracted based on the generated second object mask.

Image processing apparatus and method for object boundary stabilization in an image of a sequence of images

Various aspects of an image-processing apparatus and method to track and retain an articulated object in a sequence of image frames are disclosed. The image-processing apparatus is configured to segment each image frame in the sequence of image frames into different segmented regions that corresponds to different super-pixels. An articulated object in a first motion state is detected by non-zero temporal derivatives between a first image frame and a second image frame. A first connectivity graph of a first set of super-pixels of the first image frame, is constructed. A second connectivity graph of a second set of super-pixels of the second image frame, is further constructed. A complete object mask of the articulated object in a second motion state is generated based on the first connectivity graph and the second connectivity graph, where at least a portion of the articulated object is stationary in the second motion state.

Automated tracking and retaining of an articulated object in a sequence of image frames

An automated process of transferring an object (e.g., the head with hair) from an image into another image, or to a different location in the same image is described. The implementation is a comprehensive and fully automated approach enabling the object's transfer without intermediate intervention and support from the user. The process automates both steps: the object's delineation, and its blending into the new background as well.

Automated embedding and blending head images

Various aspects of an apparatus and a method to generate a shadow of an object embedded in a target image are disclosed herein. The method includes generation of an object mask of the embedded object in the target image. The object mask is categorized into a first category or a second category based on a pre-determined set of rules. Based on the categorization, a shadow of the object in the target image is generated. The generation of the shadow comprises dilating the categorized object mask by a predetermined multiplication factor when the categorized object mask corresponds to the first category. The generation of the shadow further comprises determination of depth information of the categorized object mask at a pre-determined height when the categorized object mask corresponds to the second category.

Apparatus and method for shadow generation of embedded objects

Image segmentation utilizing the color and brightness of sections of the image to generate super-pixels is described herein. The image segmentation is implemented pixel-wise. A color triangle is utilized in the classification of the pixels. By using a hierarchical classification table, the memory usage is significantly reduced, and the image segmentation is able to be performed on-the-fly in real-time.

Fast color-brightness-based methods for image segmentation

Automatic scaling of image objects being moved or copied to a target object location is presented. An original image and its depth map are received within which the user selects an original object and a target location for the object to be moved or copied. A center of scaling is found and a base location selected at which depth value is to be obtained at the target location for use in scaling. Target object is then scaled in response to a ratio between original object depth and target object depth. An occlusion check is made, after which non-occluded pixels are pasted to the target location to complete the move/copy which is in proper proportion and accounts for surrounding structures.

Automatic scaling of objects based on depth map for image editing

Various aspects of a method and apparatus for video processing may include a computing device communicably coupled to an external device. The computing device may be operable to determine an average vertical velocity and an average horizontal velocity of a subset of pixels in an image frame and determine a depth value for each pixel of the subset of pixels based on calculated motion vectors of the pixel of the subset of pixels, the average vertical velocity of the subset of pixels and the average horizontal velocity of the subset of pixels.

Method and apparatus for real-time conversion of 2-dimensional content to 3-dimensional content

An image processing device determines a first brightness value of a first pre-specified area in proximity to an object mask of an object in a source image and a first average color value of the source image, and determines a second brightness value of a second pre-specified area in proximity to an object mask of the object in a target image and a second average color value of the target image. The brightness value of each pixel of the object in the target image is adjusted based on a ratio of the second brightness value and the first brightness value. A color value of each pixel of an object in the target image is adjusted when a difference value between the first average color value and the second average color value exceeds a threshold color value.

System and method for color and brightness adjustment of an object in target image

A system for generating orientation information includes a reflector, an image collection system, and a processor. The image collection system is configured to collect at least two sets of image data, where one set of image data includes a stronger indication of the reflector than the other set of image data. The two sets of image data are collected using at least one reflector with some orientation-specific characteristic or a reflector integrated into a device that includes some orientation-specific structural feature. Once collected, the two sets of image data are used to generate orientation information related to the reflector. In particular, orientation information related to the reflector is generated by taking the difference between the two sets of image data.

Orientation determination utilizing a cordless device

Embodiments of the present invention use the results of a plurality of defect detecting tests and adjust the result of each test in a manner that reflects the accuracy of the test that produced it. A manufactured unit can then be evaluated using a mathematical combination of the adjusted results.

Combining multiple independent sources of information for classification of devices under test

A system and method for performing optical inspection are provided. At least one 'invariant feature' of an object design is determined, and such invariant feature is used in inspecting objects having the corresponding design. An 'invariant feature' is a feature that is invariant certain transformations occurring in a captured image of an object under inspection, such as brightness, color, and/or other transformations in the captured image. Accordingly, an inspection template may comprise information corresponding to at least one pre-selected invariant feature of an object's design. In certain embodiments, the template is a shape description of a feature that provides an intrinsic invariance to a specified set of basic transformations. Accordingly, the amount of pixel values stored in a template may be minimized, which minimizes the number of pixel comparisons made between a captured image of the object under inspection and the inspection template during the inspection analysis.

System and method for performing automated optical inspection of objects

A method and apparatus that utilize time-domain measurements of a nonlinear device produce or extract a behavioral model from embeddings of these measurements. The method of producing a behavioral model comprises applying an input signal to the nonlinear device, sampling the input signal to produce input data, measuring a response of the device to produce output data, creating an embedded data set, fitting a function to the embedded data set, and verifying the fitted function. The apparatus comprises a signal generator that produces an input signal that is applied to the nonlinear device, the device producing an output signal in response. The apparatus further comprises a data acquisition system that samples and digitizes the input and output signals and a signal processing computer that produces an embedded data set from the digitized signals, fits a function to the embedded data set, and verifies the fitted function.

Method and apparatus for extraction of nonlinear black-box behavioral models from embeddings of the time-domain measurements

A method and apparatus correct for image brightness of images taken of an object with point source illumination in an imaging system. The brightness correction method and apparatus of the present invention correct for the non-object related brightness characteristics of a point source illumination in the observed or measured brightness of a relatively planar object being imaged by the imaging system. The method and apparatus are applicable to imaging and inspection systems used with a wide variety of planar and semi-planar objects including but not limited to X-ray inspection of printed circuit boards (PCBs) and integrated circuits.

Growing community of inventors

Foster City, CA, United States of America

Daniel A Usikov