Image Blur Detection with 2D Haar Wavelet Transform and Its Effect on Skewed Barcode Scanning
نویسنده
چکیده
An algorithm is presented for image blur detection with the 2D Haar Wavelet transform (2D HWT). The algorithm classifies an image as blurred or sharp by splitting it into N x N tiles, applying several iterations of the 2D HWT to each tile, and grouping horizontally, vertically, and diagonally connected tiles with pronounced changes into tile clusters. Images with large tile clusters are classified as sharp. Images with small tile clusters are classified as blurred. If need be, the blur extent can be estimated as the ratio of the total area of the connected tile clusters and the area of the image. When evaluated on a sample of five hundred images, the algorithm performed on par or better than two other blur detection algorithms found in the literature. The effect of blur detection on skewed barcode scanning is investigated by integrating the presented blur detection algorithm into a skewed barcode scanning algorithm. The experimental results indicate that blur detection had a positive effect on skewed barcode scanning rates. Keywords—computer vision; image blur detection; Haar wavelets, 2D Haar wavelet transform, barcode scanning
منابع مشابه
Local Blur and Blocking Artifact Detection in Digital Images
In this paper, we will present a novel but simple unified method to locally detect blocking artifact and blur in digital compressed image. Digital images are prone to coding artifacts in terms of blur and blocking artifacts. Each of the distortion mentioned above has different characteristics due to coding scheme applied to the images. We present a local blur and blocking artifact detection bas...
متن کاملText Skew Angle Detection in Vision-Based Scanning of Nutrition Labels
An algorithm is presented for text skew angle detection in vision-based scanning of nutrition labels on grocery packages. The algorithm takes a nutrition label image and applies several iterations of the 2D Haar Wavelet Transform (2D HWT) to downsample the image and to compute the horizontal, vertical, and diagonal change matrices. The values of these matrices are binarized and combined into a ...
متن کاملAn Effective Technique of Image Degradation using DWT based Padding Kernel Detection
Image Filtering is a technique of removing unwanted Noise from image so that the image can be improved in terms of brightness and noise and contrast. Although there are various technique implemented for the Image Degradation and removing Noise level from image such as using Gaussian Blur. The Existing Gaussian Blur technique is an efficient technique which provides more Peak Signal to Noise Rat...
متن کاملReal Time Vehicle License Plate Recognition Based on 2D Haar Discrete Wavelet Transform
This thesis is to present a new approach for license-plate recognition using 2D Haar Discrete Wavelet Transform (HDWT) and Artificial neural Network. This thesis consists of three main parts. The first part is to locate and extract the license-plate in an image. The second part is to train of the license-plate. The third part is to real time scan recognize of the license-plate. Traditional lice...
متن کاملEdge Detection with Hessian Matrix Property Based on Wavelet Transform
In this paper, we present an edge detection method based on wavelet transform and Hessian matrix of image at each pixel. Many methods which based on wavelet transform, use wavelet transform to approximate the gradient of image and detect edges by searching the modulus maximum of gradient vectors. In our scheme, we use wavelet transform to approximate Hessian matrix of image at each pixel, too. ...
متن کامل