Standard test image

About: Standard test image is a research topic. Over the lifetime, 5217 publications have been published within this topic receiving 98486 citations.

Kernel Sparse Models for Automated Tumor Segmentation

Abstract: In this paper, we propose sparse coding-based approaches for segmentation of tumor regions from MR images. Sparse coding with data-adapted dictionaries has been successfully employed in several image recovery and vision problems. The proposed approaches obtain sparse codes for each pixel in brain magnetic resonance images considering their intensity values and location information. Since it is trivial to obtain pixel-wise sparse codes, and combining multiple features in the sparse coding setup is not straightforward, we propose to perform sparse coding in a high-dimensional feature space where non-linear similarities can be effectively modeled. We use the training data from expert-segmented images to obtain kernel dictionaries with the kernel K-lines clustering procedure. For a test image, sparse codes are computed with these kernel dictionaries, and they are used to identify the tumor regions. This approach is completely automated, and does not require user intervention to initialize the tumor regions in a test image. Furthermore, a low complexity segmentation approach based on kernel sparse codes, which allows the user to initialize the tumor region, is also presented. Results obtained with both the proposed approaches are validated against manual segmentation by an expert radiologist, and the proposed methods lead to accurate tumor identification.

System and method for online processing of video images in real time

Abstract: The invention is directed to real-time processing of video data. In some examples at least one image of the video data is processed utilizing reference data comprising reference image data of background within a region of interest and clutter image data indicative thereof, to determine a pixel deviation level of each pixel in the at least one image and generate pixel-deviation image data indicative thereof. The pixel-deviation image data is processed to enhance its tonal pixel distribution and generating enhanced image data, which is processed to determine a threshold level based on the tonal pixel distribution. A binary image map is then generated using the determined threshold level, the binary image map being indicative of the background and foreground components of the at least one image.

Vision testing system and method

Abstract: A method for testing a person's vision is disclosed. The method includes providing, for display to the person, one or more sequences of test images, each test image including one or more test symbols. For each test image, a target symbol is identified to the person. The person then views each test image in the sequence and activates a control in response to recognising a test symbol that replicates the shape of the target symbol. At the completion of the sequence, a parameter value associated with the activations is processed and correlated with a vision metric. A system for testing a person's vision is also disclosed.

Single Image Pop-Up from Discriminatively Learned Parts

Abstract: We introduce a new approach for estimating a fine grained 3D shape and continuous pose of an object from a single image. Given a training set of view exemplars, we learn and select appearance-based discriminative parts which are mapped onto the 3D model through a facility location optimization. The training set of 3D models is summarized into a set of basis shapes from which we can generalize by linear combination. Given a test image, we detect hypotheses for each part. The main challenge is to select from these hypotheses and compute the 3D pose and shape coefficients at the same time. To achieve this, we optimize a function that considers simultaneously the appearance matching of the parts as well as the geometric reprojection error. We apply the alternating direction method of multipliers (ADMM) to minimize the resulting convex function. Our main and novel contribution is the simultaneous solution for part localization and detailed 3D geometry estimation by maximizing both appearance and geometric compatibility with convex relaxation.

Image positioning device, method, and program

Abstract: PROBLEM TO BE SOLVED: To improve the registration between three-dimensional reference image data including ultrasonic image data and three-dimensional object image data such as between ultrasonic images, and between an ultrasonic image and another modality image. SOLUTION: For example, a region setting section 15 sets respective small regions E1 and E2, or positioning candidates, in reference image data R such as US (ultrasonic) image data 19-1 before a treatment and object image data F such as US image data 19-2 after the treatment at parts having anatomically characteristic images; and a positioning section 16 finds an image similarity degree between the small regions E1 and E2 and positions the reference image data R such as the US image data 19-1 before the treatment and the object image data F such as the US image data 19-2 after the treatment. COPYRIGHT: (C)2009,JPO&INPIT