![]() ![]() Further, they are often captured under variant illuminations and view angles. They appear in multiple patterns and are attached onto all kinds of surfaces, such as signage boards, walls, cars, and objects. ![]() Firstly, it is difficult to predict the fonts, sizes, colors, and deformations of text characters and strings in natural scenes. However, extracting text from natural scene images must solve three challenging problems. Text information plays a significant role in many applications including assistive navigation, image-based search, object recognition, scene understanding, and geocoding, etc., because it provides more descriptive and abstract information beyond intuitive perception of other objects. The evaluation results on benchmark datasets demonstrate that our algorithm achieves the state-of-the-art performance on scene text classification and detection, and significantly outperforms the existing algorithms for character identification. We perform three groups of experiments to evaluate the effectiveness of our proposed algorithm, including text classification, text detection, and character identification. The contributions of this paper include three aspects: 1) a new character appearance model by a structure correlation algorithm which extracts discriminative appearance features from detected interest points of character samples 2) a new text descriptor based on structons and correlatons, which model character structure by structure differences among character samples and structure component co-occurrence and 3) a new text region localization method by combining color decomposition, character contour refinement, and string line alignment to localize character candidates and refine detected text regions. ![]() Our proposed algorithm is able to model both character appearance and structure to generate representative and discriminative text descriptors. Scene text classification and detection are still open research topics. In this paper, we propose a novel algorithm to detect text information from natural scene images. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |