Scene text detection plays a significant role in various applications, such as object recognition, document management, and visual navigation. The instance segmentation based method has been mostly used in existing research due to its advantages in dealing with multi-oriented texts. However, a large number of non-text pixels exist in the labels during the model training, leading to text mis-segmentation. In this paper, we propose a novel multi-oriented scene text detection framework, which includes two main modules: character instance segmentation (one instance corresponds to one character), and character flow construction (one character flow corresponds to one word). We use feature pyramid network (FPN) to predict character and non-character instances with arbitrary directions. A joint network of FPN and bidirectional long short-term memory (BLSTM) is developed to explore the context information among isolated characters, which are finally grouped into character flows. Extensive experiments are conducted on ICDAR2013, ICDAR2015, MSRA-TD500 and MLT datasets to demonstrate the effectiveness of our approach. The F-measures are 92.62%, 88.02%, 83.69% and 77.81%, respectively.

The early detection of diabetic retinopathy is crucial for preventing blindness. However, it is time-consuming to analyze fundus images manually, especially considering the increasing amount of medical images. In this paper, we propose an automatic diabetic retinopathy screening method using color fundus images. Our approach consists of three main components: edge-guided candidate microaneurysms detection, candidates classification using mixed features, and diabetic retinopathy prediction using fused features of image level and lesion level. We divide a screening task into two sub-classification tasks: 1) verifying candidate microaneurysms by a naive Bayes classifier; 2) predicting diabetic retinopathy using a support vector machine classifier. Our approach can effectively alleviate the imbalanced class distribution problem. We evaluate our method on two public databases: Lariboisìere and Messidor, resulting in an area under the curve of 0.908 on Lariboisìere and 0.832 on Messidor. These scores demonstrate the advantages of our approach over the existing methods.

Block matching based 3D filtering methods have achieved great success in image denoising tasks. However, the manually set filtering operation could not well describe a good model to transform noisy images to clean images. In this paper, we introduce convolutional neural network (CNN) for the 3D filtering step to learn a well fitted model for denoising. With a trainable model, prior knowledge is utilized for better mapping from noisy images to clean images. This block matching and CNN joint model (BMCNN) could denoise images with different sizes and different noise intensity well, especially images with high noise levels. The experimental results demonstrate that among all competing methods, this method achieves the highest peak signal to noise ratio (PSNR) when denoising images with high noise levels (σ > 40), and the best visual quality when denoising images with all the tested noise levels.