Patent application number | Description | Published |
20100202686 | IMAGE PROCESSING METHOD, IMAGE PROCESSING APPARATUS, AND PROGRAM - A clustering unit calculates, for clusters in a descending order of the number of pixels belonging thereto, a distance from a feature vector of a processing object pixel and a representative feature vector of an object cluster, and compares the distance with a first threshold. The processing object pixel is stored in a memory or the like as a pixel belonging to an object cluster when the distance is judged to be less than or equal to the first threshold. | 08-12-2010 |
20110026841 | CLUSTERING PROCESSING METHOD, CLUSTERING PROCESSING APPARATUS, AND NON-TRANSITORY COMPUTER-READABLE MEDIUM - A clustering processing method for dividing a samples into a plurality of clusters based on a feature amount of each sample, the plurality of clusters each belonging to one of a plurality of layers composed of M layers (M=2, . . . , K), the clustering processing method comprises a sample allocating step of allocating a sample targeted for processing to a cluster belonging to a first layer, based on a result of comparing the feature amount of the target sample with a representative feature amount of each of clusters belonging to the first layer; a determination step of determining whether to allocate a cluster belonging to an M−1th layer to an Mth layer; and a cluster allocating step of allocating a cluster belonging to the M−1th layer to the Mth layer, if it is determined in the determination step to allocate a cluster belonging to the M−1th layer to the Mth layer. | 02-03-2011 |
20120288204 | IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING METHOD - An area where a specific object is captured is extracted as a specific area from the image of a frame of interest, and the evaluation value of the specific area is obtained using a predetermined evaluation formula. It is determined whether the evaluation value of the specific area in a frame preceding the frame of interest has exceeded a predetermined threshold. When it is determined that the evaluation value of the specific area has exceeded the predetermined threshold, the frame of interest is encoded to set the code amount of the specific area in the image of the frame of interest to be smaller than that of the specific area in the image of the frame preceding the frame of interest. | 11-15-2012 |
20120314765 | IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING METHOD - A specific region in each frame image input after a detection process has been completed a predetermined number of times or more is estimated from a specific region detected from a past frame before the frame. The shift between the specific region detected from a first frame image input after the detection process has been completed the predetermined number of times or more and the specific region estimated for the first frame image is obtained. When the shift falls within a predetermined range, an encoding parameter to encode the specific region estimated for a second frame image input at a point the detection process for the first frame image has been completed with a higher image quality than that of regions other than the specific region is set. | 12-13-2012 |
20120314956 | IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING METHOD - Out of regions extracted from a frame image, regions assigned the same identification information as that of a region unselected in a past frame immediately before the frame are defined as nonselection regions, and nonselection regions in number equal to or smaller than a predetermined number are selected out of the nonselection regions. | 12-13-2012 |
20130107971 | IMAGE ENCODING APPARATUS, IMAGE ENCODING METHOD AND PROGRAM, IMAGE DECODING APPARATUS, IMAGE DECODING METHOD AND PROGRAM | 05-02-2013 |
20130170545 | IMAGE ENCODING APPARATUS, IMAGE ENCODING METHOD AND PROGRAM - An image encoding apparatus includes an encoding unit which encodes an input image of a block, a calculating unit which calculates a plurality of evaluation values for the block, an identifying unit which generates identification information by comparing a plurality of evaluation values calculated by the calculating unit with a plurality of threshold values, and a controller which controls a quantization parameter on the basis of the identification information identified by the identifying unit. | 07-04-2013 |
20140064371 | IMAGE PROCESSING APPARATUS, METHOD OF CONTROLLING THE SAME, AND RECORDING MEDIUM - If the picture identifier of a first frame and the picture identifier of a second frame match, a rewriting unit rewrites the picture identifier and the slice type of the first frame. | 03-06-2014 |
20140334538 | IMAGE CODING APPARATUS, IMAGE CODING METHOD, IMAGE DECODING APPARATUS, IMAGE DECODING METHOD, AND PROGRAM - An image coding apparatus configured to divide an image into one or more slices each including a plurality of blocks and to code each slice on a block-by-block basis includes a first coding unit configured to code blocks included in a first portion of the slice, and a second coding unit configured to code blocks included in a second portion of the slice, wherein, when the second coding unit codes an initial block in the second portion, the second coding unit codes the initial included in the second portion by referring to a first quantization parameter provided to the slice as an initial value and referred to by the first coding unit when the first coding units codes the initial block in the first portion. | 11-13-2014 |
20140369617 | IMAGE ENCODING APPARATUS, IMAGE ENCODING METHOD, AND PROGRAM - An amount of code is reduced for blocks in which visible degradation is not easily susceptible, while a large amount of code is assigned to blocks whose degradation in image quality is easily perceptible thereby suppressing the number of blocks for which a process is performed to achieve high quality image and thus suppressing an increase in the total amount of code. An input image is encoded in units of blocks. A block evaluation value for the block is calculated. The block is divided into N sub-blocks where N is equal to or greater than 2, and a sub-block evaluation value is calculated for each sub-block. A quantization parameter for the block is controlled based on the block evaluation value and the sub-block evaluation values. | 12-18-2014 |