Confusion Matrix as Performance Measure for Corner Detectors

Abstract

Nowadays, corner detection algorithms have been proposed by several researchers who described them contrarily, depending on their respective viewpoints to obtain the data and information as a human eye does. Basically, no researchers have come up with a technique to compare corner detectors with another’s. Thus, this study proposed to adapt the confusion matrix technique as a performance measure for corner detectors. The judgement accuracy of every corner detector will only be pleased if the actual corner points are already known. Therefore, this study is attracted to explore the accuracy of corner detectors, namely the Global and Local Curvature Scale space (GLCSS), Affine Resilient Curvature Scale Space (ARCSS), and Harris. These corner detectors were analysed using the nine characters selected from Jawi, Chinese, and Tamil characters, three characters each, respectively. This study specifically detected the true corners for these characters using the determined corner detectors. The actual corner of all these characters was confirmed through a survey of twenty respondents. The majority of marked corners by respondents were considered actual corner points. Then, the input image for all characters was converted into a grayscale image. Every image will undergo pre-processing step, the process of boundary extraction using Canny edge detector. Thus, the edge image was extracted to get the corner point by applying the corner detectors, and the corner point detected was marked on that image. Above and beyond, the study aims to introduce a confusion matrix approach as a performance measure to carry out the most outstanding algorithm in detecting the true corner points for all the tested characters. From the evaluation, GLCSS and Harris algorithms have shown good accuracy. Henceforth, the study is not trying to judge the goodness of each corner detector but only to introduce confusion matrix as a tool that can be considered to measure the performance of the corner detector.

Mapping the distribution of sea urchin (Echinoidea) and benthic habitat using drone in the waters of Lancang Island

“…This accuracy test is known as a confusion matrix. The calculation is provided in [25]. Values for overall accuracy (OA), producer accuracy (PA), and user accuracy (UA).…”

Guidelines for Risk Evaluation in Artificial Intelligence Applications

“…Once the confusion matrix has been calculated in the AI development phase, it can be periodically recalculated a posteriori, in the operational phase, having the exact answers available, it is compared with the design matrix to check for any significant deviations, which could indicate the emergence of a risk considered mitigated or acceptable. (Ramli et al, 2022) A final step in the risk assessment and mitigation process is communication and information. In practice, this involves defining information, often common to relatively different systems, to be transferred to users, be they specialists or masses.…”

A Hybrid RBF Neural Network and FCM Clustering for Diabetes Prediction Dataset

“…Several evaluation metrics commonly used to measure model performance in predicting diabetes are Accuracy, Precision, Recall, and F1-Score. The equation for finding these values can be found using the following equations: 6, 7, 8, and 9 below (Ramli et al, 2022) (Tasnim et al, 2022).…”