A new dataset of images was produced and used to train and validate the model. In this paper an end-to-end approach using Convolutional Neural Networks (CNN) is presented to classify images into six categories of bad lighting, Gaussian blur, motion blur, JPEG 2000, white-noise, and high quality reference images. The ability to quickly and automatically classify an image as poor quality creates opportunities for a multitude of applications such as digital cameras, phones, self-driving cars, and web search technologies. The detection of poor quality images for reasons such as focus, lighting, compression, and encoding is of great importance in the field of computer vision. Needless to say, this measure can be used for various imaging applications including auto-focusing and astigmatism correction. Regardless of the detection accuracy, the proposed measure in this paper is not demanding in computation time. This method is fast, easy to implement and accurate.
This paper presents a blurriness/sharpness measure, and demonstrates its feasibility by using extensive experiments. In order to decide whether to process the images or not, or whether to delete them or not, reliable measure of image degradation to detect blurry images from sharp ones is needed. However, digital pictures can be degraded by limited contrast, inappropriate exposure, imperfection of auto-focusing or motion compensating devices, unskillfulness of the photographers, and so on. In addition, motion compensation devices are able to compensate motion causing blurriness in the images. Recently many digital cameras are equipped with various auto-focusing functions to help users take well-focused pictures as easily as possible. In this paper we present a simple, efficient method for detecting the blurry photographs.
0 kommentar(er)
