Rakuten, Inc.

Xinhao Liu

Naoki Chiba

Ryota Hinami

Shin'ichi Satoh

A character recognition device includes an acquisition means configured to acquire an image containing a character region, a first recognition means configured to recognize a character from the character region by a first recognition method, a setting means configured to set reference lines along an alignment direction of the characters and passing through a specified position in each character, a second recognition means configured to recognize a character by a second recognition method, the second recognition method being a method that recognizes a character from an image within a recognition window by scanning in a recognition target region in an image while changing a size of the recognition window, and configured to set a position or a height in a vertical direction of the recognition window based on the reference lines, and an output means configured to output a word composed of characters recognized by the second recognition means.

Character recognition device, character recognition method, and character recognition program

An image processing device according to one embodiment includes a calculation unit and a setting unit. The calculation unit calculates a degree of complexity indicating a degree of positional dispersion of edges in a target region where a text region is to be extracted. The setting unit sets an edge threshold for detecting the text region to low as the degree of complexity is low.

Image processing device, image processing method, and image processing program

An image processing device according to one embodiment includes an acquisition unit, a first specifying unit, and a second specifying unit. The acquisition unit acquires an edge between a text region where the translucent text is superimposed and a background region where the translucent text is not superimposed. The first specifying unit acquires a plurality of pairs of a representative color in the text region and a representative color in the background region adjacent to each other with the edge placed therebetween, and specifies a text color and transparency of the translucent text from the plurality of pairs. The second specifying unit specifies a pixel color before the translucent text is superimposed for each pixel in the text region from a pixel color after the translucent text is superimposed, the text color and the transparency.

Growing community of inventors

Tokyo, Japan

Xinhao Liu