An image processing apparatus according to the present invention includes a registration unit configured to register first image data as a template, a character recognition unit configured to recognize one or more character strings included in second image data different from the first image data, a display unit configured to display the one or more character strings recognized by the character recognition a reception unit configured to receive a selection of a character string displayed by the display unit, the selection being made by a user, and a storage unit configured to store the second image data in a folder named with a character string based on the selection received by the reception unit. The display unit does not display, from among of the one or more character strings recognized by the character recognition unit, a character string included in the image data registered by the registration.

An image forming apparatus includes a communication interface, an encoder, and a processor. The communication interface communicates with a cloud server that executes decoding by any of a plurality of decoding methods corresponding to a plurality of autoencoder models. The encoder performs encoding by any of a plurality of encoding methods corresponding to the plurality of autoencoder models. The processor specifies an encoding method to the encoder to encode image data into intermediate layer data that is configured to be decoded by the cloud server and transmits the intermediate layer data and model information indicating the specified encoding method used for the encoding to the cloud server through the communication interface.

An image processing system and method are described which use entropy values in processing the image. For each of a plurality of segments of an image, the segment is considered as a stream of bits and a bit difference is computed between pairs of sequential bit sequences in the stream of bits. An entropy value of the segment is computed as a function of the bit differences. The image is processing based on the computed entropy values, which may include compressing some or all of the image segments using an acceleration factor that is based on the computed entropy value for the segment. In this way, differences in entropy, which correlate with the compressibility of the image segment, can ensure an optimal compression of the segment, or in some cases, no compression.

A picture data transmission method and device are disclosed in the present invention. The picture data transmission method comprises: recoding a first picture to be transmitted, by a picture data sending terminal, to obtain a second picture, wherein the file size of the second picture is smaller than that of the first picture, and a quality difference between the second picture and the first picture is less than a pre-set threshold; and selecting one of the first picture and the second picture according to quality values of the first picture and the second picture and sending the selected picture to a picture data receiving terminal. According to the present invention, pictures can be recoded to obtain pictures with a small amount of data for data transmission, without affecting the picture quality, thereby saving network resources and reducing storage pressure.

A picture data transmission method and device are disclosed in the present invention. The picture data transmission method comprises: recoding a first picture to be transmitted, by a picture data sending terminal, to obtain a second picture, wherein the file size of the second picture is smaller than that of the first picture, and a quality difference between the second picture and the first picture is less than a pre-set threshold; and selecting one of the first picture and the second picture according to quality values of the first picture and the second picture and sending the selected picture to a picture data receiving terminal. According to the present invention, pictures can be recoded to obtain pictures with a small amount of data for data transmission, without affecting the picture quality, thereby saving network resources and reducing storage pressure.

An image processing apparatus according to the present invention includes a registration unit configured to register first image data as a template, a character recognition unit configured to recognize one or more character strings included in second image data different from the first image data, a display unit configured to display the one or more character strings recognized by the character recognition a reception unit configured to receive a selection of a character string displayed by the display unit, the selection being made by a user, and a storage unit configured to store the second image data in a folder named with a character string based on the selection received by the reception unit. The display unit does not display, from among of the one or more character strings recognized by the character recognition unit, a character string included in the image data registered by the registration.

An image processing system and method are described which use entropy values in processing the image. For each of a plurality of segments of an image, the segment is considered as a stream of bits and a bit difference is computed between pairs of sequential bit sequences in the stream of bits. An entropy value of the segment is computed as a function of the bit differences. The image is processing based on the computed entropy values, which may include compressing some or all of the image segments using an acceleration factor that is based on the computed entropy value for the segment. In this way, differences in entropy, which correlate with the compressibility of the image segment, can ensure an optimal compression of the segment, or in some cases, no compression.

Provided is an information processing apparatus including: a marking extraction circuit that extracts, from a script image including a plurality of markings respectively superimposed on a plurality of character strings, the plurality of markings; a same-character-string identification circuit that identifies the same character string out of the plurality of character strings on which the markings are respectively superimposed; and a symbol determination circuit that allocates the same symbol to the same character string and allocates different symbols to different character strings.

A device for coding video data is configured to determine that a current block of video data is coded using an intra prediction mode; add an intra prediction mode of a first neighboring block of the current block to a most probable mode candidate list for the current block; add an intra prediction mode for a second neighboring block of the current block to the most probable mode candidate list for the current block; add an intra prediction mode for a third neighboring block of the current block to the most probable mode candidate list for the current block; and code the current block of video data using an intra prediction mode.

A device for coding video data is configured to determine that a current block of video data is coded using an intra prediction mode; add an intra prediction mode of a first neighboring block of the current block to a most probable mode candidate list for the current block; add an intra prediction mode for a second neighboring block of the current block to the most probable mode candidate list for the current block; add an intra prediction mode for a third neighboring block of the current block to the most probable mode candidate list for the current block; and code the current block of video data using an intra prediction mode.