Image Pre-Processing Method of Machine Learning for Edge Detection with Image Signal Processor Enhancement

Abstract

Even though computer vision has been developing, edge detection is still one of the challenges in that field. It comes from the limitations of the complementary metal oxide semiconductor (CMOS) Image sensor used to collect the image data, and then image signal processor (ISP) is additionally required to understand the information received from each pixel and performs certain processing operations for edge detection. Even with/without ISP, as an output of hardware (camera, ISP), the original image is too raw to proceed edge detection image, because it can include extreme brightness and contrast, which is the key factor of image for edge detection. To reduce the onerousness, we propose a pre-processing method to obtain optimized brightness and contrast for improved edge detection. In the pre-processing, we extract meaningful features from image information and perform machine learning such as k-nearest neighbor (KNN), multilayer perceptron (MLP) and support vector machine (SVM) to obtain enhanced model by adjusting brightness and contrast. The comparison results of F1 score on edgy detection image of non-treated, pre-processed and pre-processed with machine learned are shown. The pre-processed with machine learned F1 result shows an average of 0.822, which is 2.7 times better results than the non-treated one. Eventually, the proposed pre-processing and machine learning method is proved as the essential method of pre-processing image from ISP in order to gain better edge detection image. In addition, if we go through the pre-processing method that we proposed, it is possible to more clearly and easily determine the object required when performing auto white balance (AWB) or auto exposure (AE) in the ISP. It helps to perform faster and more efficiently through the proactive ISP.

Image Contrast Enhancement Method Based on Nonlinear Space and Space Constraints

“…A robust method of (TAR) value, a triangular area based on K nearest neighbors (KNN), is described in [16]. Outliers were removed using geometric relations in [17].…”

Machine Vision-Based Method for Measuring and Controlling the Angle of Conductive Slip Ring Brushes

“…The general camera calibration is divided into the linear calibration method, nonlinear calibration method, two-step method, and tensor calibration method [ 25 ]. The Zhang calibration method combines the advantages of linear calibration and nonlinear calibration, and the method is simple to operate and has high accuracy, which is suitable for most occasions.…”

Performance analysis of gradient based image edge detection

“…Keumsun park et al have proposed pre-processing and machine learning method is verified as the important method of pre-processing image from image signal processor in order to gain better edge detection image. It is possible to more clearly and simply resolve the object essential when performing Auto White Balance (AWB) or Auto Exposure (AE) in the Image Signal Processing (ISP) [3]. Jian Liu et al have studiedthe adaptive multi-scale edge detection method based on canny algorithm, and through theoretical analysis, compares the advantages and disadvantages of various algorithms in image edge detection.…”