Image blur and image noise are common distortions during image acquisition. In this paper, we systematically study the effect of image distortions on the deep neural network (DNN) image classifiers. First, we examine the DNN classifier performance under four types of distortions. Second, we propose two approaches to alleviate the effect of image distortion: re-training and fine-tuning with noisy images. Our results suggest that, under certain conditions, fine-tuning with noisy images can alleviate much effect due to distorted inputs, and is more practical than re-training.

Abstract-We address the vehicle detection and classification problems using Deep Neural Networks (DNNs) approaches. Here we answer to questions that are specific to our application including how to utilize DNN for vehicle detection, what features are useful for vehicle classification, and how to extend a model trained on a limited size dataset, to the cases of extreme lighting condition. Answering these questions we propose our approach that outperforms state-of-the-art methods, and achieves promising results on image with extreme lighting conditions.

No abstract

We investigate the design of an entire mobile imaging system for early detection of melanoma. Different from previous work, we focus on smartphone-captured visible light images. Our design addresses two major challenges. First, images acquired using a smartphone under loosely-controlled environmental conditions may be subject to various distortions, and this makes melanoma detection more difficult. Second, processing performed on a smartphone is subject to stringent computation and memory constraints. In our work, we propose a detection system that is optimized to run entirely on the resourceconstrained smartphone. Our system intends to localize the skin lesion by combining a lightweight method for skin detection with a hierarchical segmentation approach using two fast segmentation methods. Moreover, we study an extensive set of image features and propose new numerical features to characterize a skin lesion. Furthermore, we propose an improved feature selection algorithm to determine a small set of discriminative features used by the final lightweight system. In addition, we study the human-computer interface (HCI) design to understand the usability and acceptance issues of the proposed system. Our extensive evaluation on an image dataset provided by National Skin Center -Singapore (117 benign nevi and 67 malignant melanoma) confirms the effectiveness of the proposed system for melanoma detection: 89.09% sensitivity at specificity ≥ 90%.

The skill of spatial learning and orientation is fundamental in humans and differs widely among individuals. Despite its importance, however, the malleability of this skill through practice has scarcely been studied empirically, in contrast to psychometric spatial ability. Thus, this article examines the possibility of improving the accuracy of configurational understanding of the environment by training. A total of 40 adults with a poor sense of direction participated in the experiment; and were randomly assigned to either a condition in which they received feedback only or a condition in which they additionally practiced allocentric spatial updating. Participants walked one route in each session, once a week for 6 weeks, and conducted spatial tasks designed to assess their knowledge of the route. A total of 20 people with an average sense of direction also participated as a comparison group. Results showed that training in allocentric spatial updating improved the accuracy of direction estimates, although the size of the effect was limited: the improvement was not large enough to equate the performance in the groups with a poor versus average sense of direction. The two groups, however, did not differ in spatial skill in mental rotation or path integration. Feedback was effective for improving accuracy in straight-line distance estimates and sketch maps: repeated trials with feedback led to improved accuracy by the sixth session to a level comparable to the group with an average sense of direction. The results show that flexible translation between viewer-centered and environment-centered representations is difficult and not readily trainable, and provide insights into the nature of individual differences in large-scale environmental cognition.