Abstract: A method and a system for detecting a scene text may include extracting a first feature map for a scene image input based on a convolutional neural network, and delivering the first feature map to a sequential deformation module; obtaining sampled feature maps corresponding to sampling positions by performing iterative sampling for the first feature map, obtaining a second feature map by performing a concatenation operation in deep learning according to a channel dimension for the first feature map and the sampled feature maps; obtaining a third feature map by performing a feature aggregation operation for the second feature map in the channel dimension, and delivering the third feature map to the object detection baseline network; and performing text area candidate box extraction for the third feature map and obtaining a text area prediction result as a scene text detection result through regression fitting.

Abstract: A method of multi-directional scene text recognition based on multi-element attention mechanism include: performing normalization processing for a text row/column image output from an external text detection module by a feature extractor, extracting a feature for the normalized image by using a deep convolutional neural network to acquire an initial feature map, adding a 2-dimensional directional positional encoding P to the initial feature map in order to output a multi-channel feature map, converting the multi-channel feature map output from a feature extractor by an encoder into a hidden representation, and converting the hidden representation output from the encoder into a recognized text by a decoder and using the recognized text as the output result.

Abstract: A method and a system of multi-directional scene text recognition based on multi-element attention mechanism are provided. The method includes: performing normalization processing for a text row/column image I output from an external text detection module by a feature extractor, extracting a feature for the normalized image by using a deep convolutional neural network to acquire an initial feature map F0, and adding a 2-dimensional directional positional encoding P to an initial feature map F0 in order to output a multi-channel feature map F; converting the multi-channel feature map F output from a feature extractor by an encoder into a hidden representation H; and converting the hidden representation H output from the encoder into a recognized text by a decoder and using the recognized text as the output result.

Abstract: A method and a system for detecting a scene text may include extracting a first feature map for a scene image input based on a convolutional neural network, and delivering the first feature map to a sequential deformation module; obtaining sampled feature maps corresponding to sampling positions by performing iterative sampling for the first feature map, obtaining a second feature map by performing a concatenation operation in deep learning according to a channel dimension for the first feature map and the sampled feature maps; obtaining a third feature map by performing a feature aggregation operation for the second feature map in the channel dimension, and delivering the third feature map to the object detection baseline network; and performing text area candidate box extraction for the third feature map and obtaining a text area prediction result as a scene text detection result through regression fitting.

Abstract: A document is divided into a plurality of regions so that each page has a meaning and, for each of the regions, there is generated a similarity table indicating a similarity degree and a data amount corresponding to the multiplexed resolution level data. By referencing this similarity table, each page of the electronic document in the region specified by the user is represented by a predetermined similarity (resolution) and at the reading speed specified by the user. Moreover, by referencing the similarity table, each page of the electronic document is represented at the maximum speed while guaranteeing the predetermined similarity.

Abstract: A document is divided into a plurality of regions so that each page has a meaning and, for each of the regions, there is generated a similarity table indicating a similarity degree and a data amount corresponding to the multiplexed resolution level data. By referencing this similarity table, each page of the electronic document in the region specified by the user is represented by a predetermined similarity (resolution) and at the reading speed specified by the user. Moreover, by referencing the similarity table, each page of the electronic document is represented at the maximum speed while guaranteeing the predetermined similarity.

Abstract: A document is divided into a plurality of regions so that each page has a meaning and, for each of the regions, there is generated a similarity table indicating a similarity degree and a data amount corresponding to the multiplexed resolution level data. By referencing this similarity table, each page of the electronic document in the region specified by the user is represented by a predetermined similarity (resolution) and at the reading speed specified by the user. Moreover, by referencing the similarity table, each page of the electronic document is represented at the maximum speed while guaranteeing the predetermined similarity.

Abstract: In an in-space viewpoint control device, a viewpoint control means comprises a recommend vector setting means, a viewpoint information determination means, a viewing point order calculation means, a viewpoint pass generating means, and a relevant information visualization control means. The recommend vector setting means sets recommend vectors for the object which reflects the intentions of the content designer. The viewpoint information determination means is determines a viewing direction and a viewpoint position in the space for viewing the object on the basis of the recommend vector information. The viewing point order calculation means is responsive when a plurality of recommend vectors are being set, as it determines a rotation order for each viewing point being determined in accordance with the recommend vector. The viewpoint pass generating means calculates an appropriate shifting pass for the viewing point following the calculated rotation order, such that the viewing point is shifted smoothly.