Text Detection in Indoor/Outdoor Scene Images
نویسندگان
چکیده
In this paper, we propose a novel methodology for text detection in indoor/outdoor scene images. The proposed methodology is based on an efficient binarization and enhancement technique followed by a suitable connected component analysis procedure. Image binarization successfully process indoor/ outdoor scene images having shadows, non-uniform illumination, low contrast and large signal-depended noise. Connected component analysis is used to define the final binary images that mainly consist of text regions. The proposed methodology leads in increased success rates at commercial OCR engines. Experimental results based on the public database of the ICDAR2003 Robust Reading Competition prove the efficiency of the proposed approach.
منابع مشابه
Character Localization From Natural Images Using Nearest Neighbours Approach
Scene text contains significant and beneficial information. Extraction and localization of scene text is used in many applications. In this paper, we propose a connected component based method to extract text from natural images. The proposed method uses color space processing. Histogram analysis and geometrical properties are used for edge detection. Character recognition is done through OCR w...
متن کاملA Framework Towards Realtime Detection and Tracking of Text
We present a near realtime text tracking system capable of detecting and tracking text on outdoor shop signs or indoor notices, at rates of up to 15 frames per second (for generous 640× 480 images), depending on scene complexity. The method is based on extracting text regions using a novel tree-based connected component filtering approach, combined with the Eigen-Transform texture descriptor. T...
متن کاملIndoor vs outdoor classification of consumer photographs using low-level and semantic features
Scene categorization to indoor vs outdoor may be approached by using low-level features for inferring high-level information about the image. Low-level features such as color and texture have been used extensively in image understanding research, however, they cannot solve the problem completely. In this paper, we propose the use of a Bayesian network for integrating knowledge from low-level an...
متن کاملIndoor Outdoor Scene Classification in Digital Images
In this paper, we present a method to classify real-world digital images into indoor and outdoor scenes. Indoor class consists of four groups: bedroom, kitchen, laboratory and library. Outdoor class consists of four groups: landscape, roads, buildings and garden. Application considers real-time system and has a dedicated data-set. Input images are pre-processed and converted into gray-scale and...
متن کاملBorder ownership assignment in real images.
We explored whether spectral based cues, such as extremal edges, are useful for border ownership classification in real images, and we analyzed how different environments: indoor vs. outdoor affect the prediction. Our algorithmic approach is based on a random forest classifier using spectral and Gestalt-like texture grouping features. The classifier detects in real-time the points in the image,...
متن کامل