Park Keumsun, Chae Minah, Cho Jae Hyuk
Department of Electronic Engineering, Soongsil University, Seoul 06978, Korea.
Micromachines (Basel). 2021 Jan 11;12(1):73. doi: 10.3390/mi12010073.
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.
尽管计算机视觉一直在发展，但边缘检测仍是该领域的挑战之一。这源于用于收集图像数据的互补金属氧化物半导体（CMOS）图像传感器的局限性，因此还需要图像信号处理器（ISP）来理解从每个像素接收到的信息，并执行某些用于边缘检测的处理操作。无论有无ISP，作为硬件（相机、ISP）的输出，原始图像都过于原始，无法进行边缘检测图像，因为它可能包含极端的亮度和对比度，而这是边缘检测图像的关键因素。为了减轻负担，我们提出一种预处理方法，以获得优化的亮度和对比度，从而改善边缘检测。在预处理中，我们从图像信息中提取有意义的特征，并执行诸如k近邻（KNN）、多层感知器（MLP）和支持向量机（SVM）等机器学习，通过调整亮度和对比度来获得增强模型。展示了未处理、预处理以及经过机器学习预处理的图像在边缘检测图像上的F1分数比较结果。经过机器学习预处理的F1结果平均为0.822，比未处理的结果好2.7倍。最终，所提出的预处理和机器学习方法被证明是对来自ISP的图像进行预处理以获得更好边缘检测图像的必要方法。此外，如果我们采用我们提出的预处理方法，那么在ISP中执行自动白平衡（AWB）或自动曝光（AE）时，就可以更清晰、轻松地确定所需对象。它有助于通过主动的ISP更快、更高效地执行。
