摘要:
Disclosed is a method for recognizing multi-language printed documents, a method for extracting character features according to the present invention, the method comprising the steps of: a) normalizing characters to a fixed size; b) converting the size-fixed characters into mesh-type characters; c) extracting stroke features of each of the mesh-type characters; d) extracting non-stroke features of each of the mesh-type characters; and e) extracting the character features using the stroke features and the non-stroke features. The present invention provides a high recognition rate irrespective of the size and modification of the characters, by extracting the character feature from the stroke and non-stroke in the mesh block.
摘要:
An image signature creating method includes: creating a map by partitioning a still image using rings defined by concentric circles radially spaced apart from each other by a predetermined interval and radial lines circumferentially spaced apart from each other by a predetermined angle, the center of the still image being that of the concentric circles; and creating an image signature from the created map on the basis of distribution of pixels in regions defined by the rings and the radial lines. Accordingly, distribution of illegal contents is prevented and interrupted by search for and discrimination of a still image illegally deformed by a copying of or an intended attack on the still image.
摘要:
An index database creating apparatus includes a feature extracting unit for extracting features from a content; an index creating unit for creating feature indices of the extracted features; an index selector for selecting one or more of the feature indices based on frequency-based importance levels thereof; and a feature index database for storing therein the selected feature indices along with locations thereof in the content. The index selector obtains the frequency-based importance levels based on frequency distributions of the feature indices in the content and in other contents to be stored in the feature index database.
摘要:
A system for managing and searching for a digital video includes: a video feature point extraction unit decoding an input video and extracting a feature point; a video feature point database (DB) storing and managing a feature point of a video to be compared (i.e., a comparison target video), and a video feature point comparison unit coarsely comparing the feature point of the input video and that of the comparison target video to acquire a candidate group, and minutely comparing the candidate group to detect a content repeated section, and informing a user of the content repeated section.
摘要:
There is provided a method of identifying User-Created Content (UCC) using an image identifier, including combining a still image with the image identifier, requesting registration of UCC corresponding to the still image combined with the image identifier, and combining a UCC identifier, issued in response to the request, with the still image combined with the image identifier, thus generating final UCC.
摘要:
In an apparatus for embedding digital watermarks into an image, a watermark embedding region extraction unit extracts an image region to contain watermarks from a wavelet transformed entire image. A watermark generation unit generates a watermark data row to be embedded according to a user's private key. A normalization operation unit normalizes the quantized data value by using a quantization unit into a normalized data value. An inverse quantization inversely quantizes and outputs the normalized data value. A watermark embedment unit embeds a watermark-embedded data value as a corresponding pixel data value into the watermark embedding region, wherein the watermark-embedded data value is obtained by subtracting, from the inversely quantized data value, the watermark data value added prior to the quantization.
摘要:
An index database creating apparatus includes a feature extracting unit for extracting features from a content; an index creating unit for creating feature indices of the extracted features; an index selector for selecting one or more of the feature indices based on frequency-based importance levels thereof; and a feature index database for storing therein the selected feature indices along with locations thereof in the content. The index selector obtains the frequency-based importance levels based on frequency distributions of the feature indices in the content and in other contents to be stored in the feature index database.
摘要:
An image classifying apparatus may include a database constructor which constructs database by detecting face region from received classification target image, extracting face feature descriptor from detected face region, extracting a costume feature descriptor using position information of detected face region, and storing face feature descriptor and costume feature descriptor in database, a first processor which generates representative image model by comparing face feature descriptor and costume feature descriptor of classification target image stored in database based on a received representative image to search for a similar image and registering similar image in a representative image model for each person, and second processor which compares additional information of representative image stored in representative image model for each person and additional information of classification target image stored in database and classifies image for each person based on similarity measured by adding up weights corresponding to similarities according to comparison results.
摘要:
An image signature creating method includes: creating a map by partitioning a still image using rings defined by concentric circles radially spaced apart from each other by a predetermined interval and radial lines circumferentially spaced apart from each other by a predetermined angle, the center of the still image being that of the concentric circles; and creating an image signature from the created map on the basis of distribution of pixels in regions defined by the rings and the radial lines. Accordingly, distribution of illegal contents is prevented and interrupted by search for and discrimination of a still image illegally deformed by a copying of or an intended attack on the still image.
摘要:
An apparatus and method for inserting/extracting a nonblind watermark using features of digital media data are provided. The apparatus and method inserts a watermark adaptively using watermark-related information determined by analyzing the characteristics of digital media data, also extracts features of the digital media data, automatically searches original media data corresponding to the features, and simultaneously and efficiently extracts a watermark using watermark-related information. Therefore, When the watermark is extracted, the original media data can be searched automatically.