SNOOPERTEXT: A MULTIRESOLUTION SYSTEM FOR TEXT DETECTION IN COMPLEX VISUAL SCENES

Autor(es)

Minetto, R. ; Thome, N. ; Cord, M. ; Fabrizio, J. ; Marcotegui, B. ; IEEE

• Tipo de documento: Artigo Científico
• Fonte: 2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING; v. N/A, p. 4-pg., 2010-01-01.

Resumo

Text detection in natural images remains a very challenging task. For instance, in an urban context, the detection is very difficult due to large variations in terms of shape, size, color, orientation, and the image may be blurred or have irregular illumination, etc. In this paper, we describe a robust and accurate multiresolution approach to detect and classify text regions in such scenarios. Based on generation/validation paradigm, we first segment images to detect character regions with a multiresolution algorithm able to manage large character size variations. The segmented regions are then filtered out using shape-based classification, and neighboring characters are merged to generate text hypotheses. A validation step computes a region signature based on texture analysis to reject false positives. We evaluate our algorithm in two challenging databases, achieving very good results. (AU)

• Processo FAPESP: 07/54201-6 - Análise de vídeos digitais: problemas de segmentação espaço-temporal, detecção de movimentos baseados em fluxo ótico e seleção de frames representativos
• Beneficiário: Rodrigo Minetto
• Modalidade de apoio: Bolsas no Brasil - Doutorado