30 results about "Stroke extraction" patented technology

The present invention discloses a method and a device for touching character segmentation in character recognition, and belongs to the character recognition field. The method comprises the steps of carrying out preprocessing to obtain connected domains, an average character width and an average character height of a row image; carrying out connected domain analysis, marking touching connected domains, carrying out stroke extraction for selected touching connected domains, carrying out segmentation point detection of the touching connected domains to obtain pre-segmentation points, and saving character blocks for non-touching connected domains; merging extracted strokes according to the pre-segmentation points to obtain the character blocks; saving the character blocks and turning to a next connected domain for carrying out touching determination, and outputting a character block sequence after all connected domains having been traversed; and merging the character blocks according to reference information and outputting recognition result. The method and the device provided in the invention merge the strokes according to the pre-segmentation points to obtain the character blocks, guaranteeing that segmentation points in a larger scope can be detected, and take the mode that contour information is used to predetect the segmentation points as a parameter in merging, avoiding merging mistakes caused by merging correct segmentation points.

The invention belongs to the technical field of image processing, and specifically relates to a position-constrained method for extracting strokes of the same name in handwritten Chinese characters. question. The method of the present invention includes: obtaining the handwritten Chinese character image and the reference Chinese character image; centering the foreground areas of the handwritten Chinese character image and the reference Chinese character image respectively in two empty images as the first and second images; obtaining the segmented and connected images of the first image area; traverse the segmented connected area of ​​the first image, and adjust the position of the reference stroke in the second image; obtain the connected area of ​​the stroke with the same name in the first image; output the point set corresponding to the connected area of ​​the stroke with the same name and its outer contour. The invention solves the problem that the stroke extraction of handwritten Chinese characters with the same name needs to pay attention to both the overall font and stroke arrangement, and improves the applicability and accuracy of the stroke extraction of the handwritten Chinese characters with the same name.

The present application provides an image recognition processing method, device, electronic equipment, and storage medium; applied to the field of maps; the method includes: identifying at least one text area image from the image to be processed, and performing text recognition on each text area image processing to obtain the font text corresponding to each text area image in the font library; stroke extraction processing is performed on the text area image to obtain the stroke extraction result of at least one stroke frame in the text area image; based on the strokes of each stroke frame in the text area image The stroke alignment processing is performed on the extraction result and the font text corresponding to the text area image to obtain the stroke correspondence between each stroke frame in the text area image and the strokes of the font text corresponding to the text area image; through this application, it is possible to accurately and efficiently The strokes are identified from the image including the characters and correspond to the strokes of the characters in the font library.

The invention provides a method for automatically extracting strokes of Chinese characters based on manifold learning, which belongs to the fields of artificial intelligence and computer graphics. This method guides the stroke extraction of the target character by constructing a two-dimensional manifold space of the Chinese character skeleton and finding the character with the most similar style as a reference character. The invention can solve the problem that the styles of the reference character and the target character are too different in the data-driven automatic stroke extraction method, and effectively improves the accuracy rate of stroke extraction of Chinese characters.

The invention discloses an off-line Chinese character stroke extraction method based on template matching. The off-line Chinese character stroke extraction method comprises the following steps: stroke codes are established for all strokes of Chinese characters and serve as templates; a code is established for a given Chinese character according to the types and numbers of the strokes and serve as a template; the framework line of the given off-line Chinese character is extracted; the framework line is dismantled into four types of stroke segments according to the directions of four strokes namely transverse, vertical, left-falling and right-falling; the stroke segments, which can possibly form new strokes through end-to-end connection, are connected to form new quasi-strokes, and the new quasi-strokes are identified according to the directions and the stroke segment composition features; the quasi-strokes, the stroke code template of the given Chinese character and the Chinese character code templates are matched to confirm all strokes of the off-line Chinese character. With adoption of the method capable of extracting the strokes of the off-line Chinese character through the framework, confirmation of each stroke of the off-line Chinese character can be facilitated, and support can be provided for giving dynamic writing attributes to the strokes of the off-line Chinese character and even the whole off-line Chinese character and for researching and developing the generation technology of a new Chinese character font library.

The invention discloses a soft-pen Chinese character conversion method based on the edition of handwriting characteristics. The above method can be used for extracting the handwriting characteristics of Chinese characters in an inscription / soft-pen copybook and generating soft-pen Chinese characters that are customized in handwriting characteristics. The method comprises the steps of firstly, selecting an appropriate noise-reduction algorithm, a binary operation and a contour smoothing method to pre-process an original inscription image and improve the contrast ratio of the inscription image relative to a background; secondly, positioning each single Chinese character through the segmenting and normalizing operation; thirdly, realizing a stroke extraction and optimization algorithm based on contour triangulation, constructing a triangular mesh for Chinese characters based on the above pre-processing operation, and marking out stroke segments; at the same time, dividing stroke sets based on handwriting characteristics; and finally, providing a Chinese character distortion generating algorithm based on stroke characteristics. According to the technical scheme of the invention, in combination of a customized characteristic matrix composed of stroke center lines, width, contraction speed, flexibility and other factors, and inputted distortion requirements, the characteristic matrix is modified. Therefore, Chinese character images of different handwriting characteristics can be generated.

The invention discloses a method for automatically extracting strokes of Chinese characters based on splitting and matching, which belongs to the technical field of pattern recognition and information processing. The skeleton diagram of stroke parts, find the intersection point in the skeleton diagram, and then calculate the PBOD curve of the two-dimensional neighborhood midpoint of the intersection point in the binary image, and extract the intersection area; 3. Extract features for stroke parts, the feature Matching with the features of the stroke components in the standard library; 4. Combining the stroke segments according to the matching results to obtain the strokes of Chinese characters. The present invention can achieve satisfactory extraction effects for Chinese characters with different fonts, effectively improve the unsatisfactory extraction accuracy and slow extraction speed of Chinese character strokes, and the accuracy of stroke extraction is also getting better as the standard font library becomes more and more comprehensive. come higher.

The invention discloses a method for extracting single-character strokes in calligraphy works. The skeleton strokes of individual characters in calligraphy works are obtained by using a skeleton crawler unit, the stroke width of each stroke of the original single-character in calligraphy works is calculated, and the minimum enclosing area of ​​the outline of the skeleton strokes is obtained. , analyze the relationship between different types of skeleton intersections and the minimum enclosing area of ​​the stroke outline, locate the shared area and determine the type of the shared area, and complete the stroke extraction according to the type of the shared area and the minimum enclosing area of ​​the skeleton stroke outline. The invention can lay a foundation for stroke-based calligraphy character recognition, calligraphy style comparison, and authenticity identification of calligraphy works. By adopting the algorithm provided by the invention, single-character strokes in calligraphy works can be completely extracted, and a stroke extraction method is provided for stroke-based calligraphy character classification, recognition, reconstruction, animation simulation and other related research and applications.

The invention belongs to the field of computer vision and pattern recognition, and specifically relates to a method and system for extracting strokes of Chinese character images based on a fully convolutional neural network, aiming to solve the problem of difficulty in extracting strokes of handwritten characters for free writing. The method of the present invention includes: extracting the region of the acquired Chinese character image; performing skeletonization operation on the overlapping region and non-overlapping region; calculating the coherence between any stroke segments in the skeletonized overlapping region; Stroke segments that belong to the same stroke are connected, and the stroke segments that are directly connected in the non-overlapping area are merged into a complete skeleton shape stroke. On the one hand, the present invention can still realize the stroke extraction of handwritten Chinese characters when the strokes of free-writing handwritten Chinese characters overlap; , greatly saving labor costs.

The invention discloses a text line detection method and device. The text line detection method comprises: a gray level decomposition step: carrying out gray level decomposition on a gray level image to acquire a text layer of the gray level image; a stroke extraction step: carrying out stroke extraction on the gray level image to acquire a stroke layer of the gray level image; a consistency verification step: verifying the consistency of connected domains of the text layer and the stroke layer, and removing the connected domain belonging to the background region of the gray level image from the text layer based on the verified result; and a text line generation step: organizing connected domains in a text layer, in which the connected domains belonging to the background region of the gray level image are removed, into a text line.. By utilizing the text line detection method and device provided by the invention, the text line which has a relative complex background and is displayed in the image or a video frame can be detected effectively and efficiently.