Fengying Xie

Automatic Fastener Classification and Defect Detection in Vision-Based Railway Inspection Systems

The detection of fastener defects is an important task in railway inspection systems, and it is frequently performed to ensure the safety of train traffic. Traditional inspection is usually operated by trained workers who walk along railway lines to search for potential risks. However, the manual inspection is very slow, costly, and dangerous. This paper proposes an automatic visual inspection system for detecting partially worn and completely missing fasteners using probabilistic topic model. Specifically, our method is able to simultaneously model diverse types of fasteners with different orientations and illumination conditions using unlabeled data. To assess the damages, the test fasteners are compared with the trained models and automatically ranked into three levels based on the likelihood probability. The experimental results demonstrate the effectiveness of this method.

Automatic segmentation of dermoscopy images using self-generating neural networks seeded by genetic algorithm

A novel dermoscopy image segmentation algorithm is proposed using a combination of a self-generating neural network (SGNN) and the genetic algorithm (GA). Optimal samples are selected as seeds using GA; taking these seeds as initial neuron trees, a self-generating neural forest (SGNF) is generated by training the rest of the samples using SGNN. Next the number of clusters is determined by optimizing the SD index of cluster validity, and clustering is completed by treating each neuron tree as a cluster. Since SGNN often delivers inconsistent cluster partitions owing to sensitivity relative to the input order of the training samples, GA is combined with SGNN to optimize and stabilize the clustering result. In the post-processing phase, the clusters are merged into lesion and background skin, yielding the segmented dermoscopy image. A series of experiments on the proposed model and the other automatic segmentation methods (including Otsus thresholding method, k-means, fuzzy c-means (FCM) and statistical region merging (SRM)) reveals that the optimized model delivers better accuracy and segmentation results.

PDE-based unsupervised repair of hair-occluded information in dermoscopy images of melanoma

The repair of hair-occluded information is one of the key problems for the precise segmentation and analysis of the skin malignant melanoma image with hairs. Aimed at dermoscopy images of pigmented skin lesions, an unsupervised repair algorithm for the hair-occluded information is proposed in this paper. This algorithm includes three steps: first, the melanoma image with hairs are enhanced by morphologic closing-based top-hat operator and then segmented through statistic threshold; second, the hairs are extracted based on the elongate of connected region; third, the hair-occluded information is repaired by the PDE-based image inpainting. As a matter of fact, with the morphologic closing-based top-hat operator both strong and weak hairs can be enhanced simultaneously, and the elongate state of band-like connected region can be correctly described by the elongate function proposed in this paper so as to measure the hair effectively. Therefore, the unsupervised repair problem of the hair-occluded information can be resolved very well through combining the hair extracting with the image inpainting technology. The experiment results show that the repaired images can satisfy the requirement of medical diagnosis by the proposed algorithm and the segmentation veracity is effectively improved after repairing the hair-occluded information.

Haze Removal for a Single Remote Sensing Image Based on Deformed Haze Imaging Model

The contrast of remote sensing images captured in haze condition is poor, which influences their interpretation. In this letter, a novel dehazing algorithm based on the deformed haze imaging model is proposed. First, the model is deformed by introducing a translation term. Second, the atmospheric light and transmission are estimated according to the new model combined with dark channel prior. Lastly, the haze is successfully removed from remote sensing images using the proposed estimation algorithm. The estimated transmission is insensitive to the texture of ground objects, and the dehazing effect for nonuniform haze is more satisfactory than the compared method. Moreover, our approach can be used for general haze removal through adjusting the translation term. Experimental results reveal that the proposed method can recover the real scene clearly from haze remote sensing images along with the advantage of good color consistency.

Melanoma Classification on Dermoscopy Images Using a Neural Network Ensemble Model

We develop a novel method for classifying melanocytic tumors as benign or malignant by the analysis of digital dermoscopy images. The algorithm follows three steps: first, lesions are extracted using a self-generating neural network (SGNN); second, features descriptive of tumor color, texture and border are extracted; and third, lesion objects are classified using a classifier based on a neural network ensemble model. In clinical situations, lesions occur that are too large to be entirely contained within the dermoscopy image. To deal with this difficult presentation, new border features are proposed, which are able to effectively characterize border irregularities on both complete lesions and incomplete lesions. In our model, a network ensemble classifier is designed that combines back propagation (BP) neural networks with fuzzy neural networks to achieve improved performance. Experiments are carried out on two diverse dermoscopy databases that include images of both the xanthous and caucasian races. The results show that classification accuracy is greatly enhanced by the use of the new border features and the proposed classifier model.

No Reference Uneven Illumination Assessment for Dermoscopy Images

For the dermoscopy image, uneven illumination will influence segmentation accuracy and lead to wrong aided diagnosis result. In this paper, a no reference uneven illumination assessment metric is proposed for dermoscopy images. Firstly, the distorted image is decomposed to illumination and reflectance components through variational framework for Retinex (VFR). Then, the illumination component is extracted by basis function fitting. Lastly, average gradient of the illumination component (AGIC) is calculated as the uneven illumination metric. A series of experiments show that, the proposed illumination extraction method is insensitive to the image content, and the proposed metric delivers an accurate illumination assessment result.

No Reference Quality Assessment for Multiply-Distorted Images Based on an Improved Bag-of-Words Model

Multiple distortion assessment is a big challenge in image quality assessment (IQA). In this letter, a no reference IQA model for multiply-distorted images is proposed. The features, which are sensitive to each distortion type even in the presence of other distortions, are first selected from three kinds of NSS features. An improved Bag-of-Words (BoW) model is then applied to encode the selected features. Lastly, a simple yet effective linear combination is used to map the image features to the quality score. The combination weights are obtained through lasso regression. A series of experiments show that the feature selection strategy and the improved BoW model are effective in improving the accuracy of quality prediction for multiple distortion IQA. Compared with other algorithms, the proposed method delivers the best result for multiple distortion IQA.

Broken Railway Fastener Detection Based on Adaboost Algorithm

The detection of broken railway fastener is important to ensure the safety of the railway transport. This paper proposes an efficient method to detect and recognize the broken fastener with complex ballast railway images. Firstly, a from-coarse-to-fine strategy according to the sleeper region’s gray and gradient characteristics is used to position the fastener, then the Haar-like feature set according to the fastener’s geometrical characteristics is introduced. Finally, the fastener state is recognized by the AdaBoost-based algorithm. The method can detect fastener effectively and automatically with high positioning and recognizing accuracy and need not manual intervention. The experiment showed that the detection rate is satisfactory.

Automatic segmentation of dermoscopy images using saliency combined with Otsu threshold

Segmentation is one of the crucial steps for the computer-aided diagnosis (CAD) of skin cancer with dermoscopy images. To accurately extract lesion borders from dermoscopy images, a novel automatic segmentation algorithm using saliency combined with Otsu threshold is proposed in this paper, which includes enhancement and segmentation stages. In the enhancement stage, prior information on healthy skin is extracted, and the color saliency map and brightness saliency map are constructed respectively. By fusing the two saliency maps, the final enhanced image is obtained. In the segmentation stage, according to the histogram distribution of the enhanced image, an optimization function is designed to adjust the traditional Otsu threshold method to obtain more accurate lesion borders. The proposed model is validated from enhancement effectiveness and segmentation accuracy. Experimental results demonstrate that our method is robust and performs better than other state-of-the-art methods.

Cloud detection of remote sensing images by deep learning

Cloud detection plays a major role for remote sensing image processing. Most of the existed cloud detection methods use the low-level feature of the cloud, which often cause error result especially for thin cloud and complex scene. In this paper, a novel cloud detection method based on deep learning framework is proposed. The designed deep Convolutional Neural Networks (CNNs) consists of four convolutional layers and two fully-connected layers, which can mine the deep features of cloud. The image is firstly clustered into superpixels as sub-region through simple linear iterative cluster (SLIC) method. Through the designed network model, the probability of each superpixel that belongs to cloud region is predicted, so that the cloud probability map of the image is generated. Lastly, the cloud region is obtained according to the gradient of the cloud map. Through the proposed method, both thin cloud and thick cloud can be detected well, and the result is insensitive to complex scene. Experimental results indicate that the proposed method is more robust and effective than compared methods.