Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 2. Отображено 2.
23-04-2014 дата публикации

Optical character recognition method based on LVQ neural network

Номер: CN103745213A
Автор: ZHANG YUXIN, LI YONGGANG, HE JIANWEI, ZHOU LINQI, GUO LIBING, LI XIANGMING, MAO WENHAO, LI QINGMEI, HU SHANGCHENG, ZHANG LONG
Принадлежит:

The invention relates to an optical character recognition method based on an LVQ (Learning Vector Quantization) neural network. The method includes the following steps: performing preprocessing including image denoising, character segmentation, binaryzation and characteristic extraction on a to-be-recognized character image; sending a single character characteristic into an input layer of the LVQ neural network and acquiring a winning competition-layer nerve cell according to a competition algorithm and performing a recognition rejection test; and inputting a character characteristic which complies with a recognition condition to the competition layer of the LVQ neural network for recognition and outputting the recognition result. The optical character recognition method based on the LVQ neural network is applicable to the field of automatic recognition of a small character set which has strict demands on false rate.

Подробнее
Номер записи: 1
08-08-2023 дата публикации

Large-scale mosaic line extraction method based on gray cost

Номер: CN116563725A
Автор: HONG ZHONGHUA, HU SHANGCHENG, ZHOU RUYAN, PAN HAIYAN, MA ZHENLING, ZHANG YUN, HAN YANLING, WANG JING, YANG SHUHU, XU LIJUN
Принадлежит:

The invention discloses a gray cost-based large-scale mosaic line extraction method, which comprises the following steps of: calculating an overlapping region of two adjacent orthoimages, and extracting a contour point set of the overlapping region; according to the contour point set, calculating skeleton points and bisectors of the overlapping area and constructing a weighted graph, then using a Dijkstra algorithm to find a minimum path between a starting point and a stopping point as an initial mosaic line, and cutting the contour area of each orthoimage according to the initial mosaic line to construct an initial mosaic line network; using an improved A star search algorithm to calculate a minimum cost path reaching a termination point according to a dynamically adjusted cost function from a starting point of an initial mosaic line as a final mosaic line, so as to optimize an initial mosaic line network, and performing re-projection mosaic on effective areas of two adjacent orthoimages ...

Подробнее
Номер записи: 2