Chengzuo Qi

Stroke Detector and Structure Based Models for Character Recognition: A Comparative Study

Characters, which are man-made symbols composed of strokes arranged in a certain structure, could provide semantic information and play an indispensable role in our daily life. In this paper, we try to make use of the intrinsic characteristics of characters and explore the stroke and structure-based methods for character recognition. First, we introduce two existing part-based models to recognize characters by detecting the elastic strokelike parts. In order to utilize strokes of various scales, we propose to learn the discriminative multi-scale stroke detector-based representation (DMSDR) for characters. However, the part-based models and DMSDR need to manually label the parts or key points for training. In order to learn the discriminative stroke detectors automatically, we further propose the discriminative spatiality embedded dictionary learning-based representation (DSEDR) for character recognition. We make a comparative study of the performance of the tree-structured model (TSM), mixtures-of-parts TSM, DMSDR, and DSEDR for character recognition on three challenging scene character recognition (SCR) data sets as well as two handwritten digits recognition data sets. A series of experiments is done on these data sets with various experimental setup. The experimental results demonstrate the suitability of stroke detector-based models for recognizing characters with deformations and distortions, especially in the case of limited training samples.

Multi-order co-occurrence activations encoded with Fisher Vector for scene character recognition

Abstract Scene character recognition remains a challenging task due to many interference factors. Considering that characters are composed of a series of parts arranged in certain structures, in this paper, we propose a novel representation termed multi-order co-occurrence activations (MCA) encoded with Fisher Vector (FV), namely MCA-FV. It implicitly models the co-occurrence information of discriminative character parts at different orders to boost the recognition performance. We first extract convolutional activations as local descriptors of character parts from convolutional neural networks (CNNs). Then, we introduce MCA features to capture the multi-order co-occurrence cues among different discriminative character parts. Finally, we apply FV to encode co-occurrence features of each order and obtain a global representation of MCA-FV. The proposed method is evaluated on four scene character datasets including English and Chinese datasets. Experiment results demonstrate the effectiveness of the proposed method for scene character recognition.

Logo Retrieval Using Logo Proposals and Adaptive Weighted Pooling

This letter presents a novel approach for logo retrieval. Considering the fact that logo only occupies a small portion of an image, we apply Faster R-CNN to detect logo proposals first, and then use a two-step pooling strategy with adaptive weight to obtain an accurate global signature. The adaptive weighted pooling method can effectively balance the recall and precision of proposals by incorporating the probability of each proposal being a logo. Experimental results show that the proposed method interprets the similarity between query and database image more accurately and achieves state of the art performance.

CRF based text detection for natural scene images using convolutional neural network and context information

This paper presents a novel scene text detection method based on conditional random field (CRF) framework. We estimate the confidence of Maximally Stable Extremal Region (MSER) being text by leveraging convolutional neural network (CNN) to define the unary cost item. In addition, we establish the neighboring interactions for MSERs using four different features including color, shape, stroke and spatial features to define the pairwise cost item. Considering the special layout of texts appearing in natural scene images, we employ context information to recover missing text MSER candidates. Furthermore, text MSERs are grouped into candidate text lines which are verified with shape-specific classifiers by integrating gray and binary features. Experimental results on four public benchmark datasets show that the proposed method achieves the comparable performance.

Spatial weighted fisher vector for image retrieval

Several recent works interpret convolutional features produced by deep convolutional neural networks as local descriptors. Existing high-dimensional aggregation based methods, e.g., Fisher Vector (FV) obtain inferior performance to pooling based methods in most situations, and we observe that it is mainly caused by the ignorance of spatial weights. In this paper, we propose a novel method named spatial weighted Fisher Vector (SWFV) to enhance the representation of FV by injecting the spatial weight map to FV. In addition, we further analyze the distribution of spatial weights and propose truncated spatial weighted FV (TSWFV). Experimental results on two benchmark datasets demonstrate that the two proposed methods achieve competitive results compared with other global representation based methods.