Methods, systems, articles of manufacture and apparatus are disclosed to label text on images. An example apparatus includes colorizer circuitry to apply color to text boxes corresponding to optical character recognition (OCR) data associated with an image, OCR manager circuitry to render an OCR text prompt associated with the OCR data, the OCR text prompt to be rendered proximate to respective ones of the text boxes, the OCR text prompt to display a text portion of the OCR data, and edit circuitry to (a) render an interface in response to selection of the OCR text prompt, the interface populated with the text portion of the OCR data, and (b) in response to an overwrite input to the interface, update the text portion of the OCR data in a memory corresponding to the image.

A method for managing drawing data including raster data includes: vectorizing, by a computer, the drawing data to generate vector data; generating, by the computer, dimension line data associated with first and second nodes included in the vector data; performing, by the computer, character recognition on a corresponding region in the drawing data corresponding to a close region close to a dimension line represented by the dimension line data; storing, by the computer, a character obtained by the character recognition as a dimension value in association with the dimension line data; and calculating, by the computer, a number of pixels per 1 mm on a drawing represented by the drawing data using the dimension value.

A method may include obtaining an image that includes a connected component that includes a set of pixels, calculating a representative color for the set of pixels, mapping the representative color to an application color in an application color palette of an application, and generating an electronic document that includes a revised version of the connected component in the application color.

A method for image processing that includes: obtaining a mask of a connected component (CC) from an image; generating a stroke width transform (SWT) image based on the mask; calculating multiple stroke width parameters for the mask based on the SWT image; identifying a hole in the CC of the mask; calculating a stroke width estimate for the hole based on the stroke width values of pixels in the SWT image surrounding the hole; generating a comparison of the stroke width estimate for the hole with a limit based on the multiple stroke width parameters for the mask; and generating a revised mask by filling the hole in response to the comparison.

Embodiments of the present application disclose a character coordinate extraction method and apparatus, a device, a medium and a program product. The method comprises: inputting a target text image into a feature extraction backbone network, and obtaining character segmentation features and text line segmentation features by means of feature fusion by different layers in the backbone network; respectively inputting the character segmentation features and the text segmentation features into a character segmentation module and a text line segmentation module, and obtaining a character segmentation heat map and a text segmentation heat map of the target text image, wherein the character segmentation module and the text line segmentation module form a segmentation network model; and calculating coordinates of a single character in the target text image according to the character segmentation heat map and the text line segmentation heat map. According to the embodiments of the present application, repeated extraction of features is reduced; high robustness is achieved for character segmentation; convergence of the network is accelerated, and the segmentation efficiency of the network is improved; the accuracy of single-character coordinate extraction is improved.

A system and methods for selecting a region of pixels in an image displayed on a touch-sensitive interface is disclosed. The method for selecting the region of pixels is based on determined connectivity of pixels in the image indicating content of the image and includes determining connected pixels on the image representing the content without performing character recognition, detecting a text selection gesture indicative of selecting the region in the image, determining coordinates of the text selection gesture performed on the touch-sensitive interface and selecting the region in the image by bounding a first set of pixels located at a proximity from the coordinates of the text selection gesture.

The invention provides an English word image recognition method, mainly loading a to-be-recognized image and performing a one-dimensional convolutional neural network operation and a fully connected operation processing to generate a feature map, outputting the feature map by a bidirectional long short-term memory (LSTM) network and performing a fully connected operation to generate a feature map, then performing a probability recognition and outputting a probabilistic string, and then recognizing the probabilistic string and outputting a word recognition result to solve the problem of producing a large amount of operation in the conventional two-dimensional recognition operation, thereby achieving efficacies of reducing costs of recognition equipment and enabling fast and accurate recognition.

A method for managing drawing data including raster data, including: vectorizing the drawing data to generate vector data; generating dimension line data associated with first and second nodes included in the vector data; performing character recognition on a corresponding region in the drawing data corresponding to a close region close to a dimension line represented by the dimension line data; and storing a character obtained by the character recognition as a dimension value in association with the dimension line data.

Coding an image that includes text content and a background is disclosed. Text portions are identified in the image. The text portions are extracted from the image to obtain a background image, where the background image includes holes corresponding to respective areas of the text portions within the image. A filled-in background image is obtained based on the background image. The filled-in background image is encoded into a compressed bitstream using a block-based encoder. The text portions is also encoded into the compressed bitstream. Encoding the text portions includes encoding respective high quality text binarization upscaled binary maps.

Provided are a method and a device for recognizing an ancient book. The method comprises: extracting classification features of a target ancient book image based on a backbone network to obtain backbone classification features; detecting the backbone classification features and determining individual character positions and text line positions included in the target ancient book image; recognizing the individual character positions to obtain content information of individual characters, and predicting the text line positions to obtain a reading order of characters in the text line positions; and arranging, based on a ratio between the individual character positions and the text line positions, the content information of the individual characters following the reading order of the characters in the text line positions to obtain a recognition result of characters in the target ancient book image.