Illumination Invariant Method Research Articles

License plate detection for multi-national vehicles: An illumination invariant approach in multi-lane environment

Only a few methods in literature are effective for multi-national license plate detection in a multi-lane scenario. These methods are prone to illumination variance, complex background and weak-edged license plates. In this paper, we propose a novel illumination invariant method to handle multi-national vehicle license plates of different colors and styles. Red corona is initially used to detect the tail-lights of vehicles to establish region-of-interest as the license plates are in a vicinity of its tail-lights. The vertical edges within each region-of-interest are obtained using a unique approach that preserve license plate edges for improved performance. Heuristic energy map is then used to distinguish the license plate area. To validate the detected regions, high-level features extracted from AlexNet Convolutional Neural Network are used. Extensive experiments on the license plates of six countries show that the proposed approach not only ensures real-time performance, but also outperforms the conventional and deep-learning methods.

Background subtraction via colour coherence under varying illuminations

An illumination-invariant method for background subtraction is presented. Inspired by the observation that the degree of dispersion in the colour space, which is computed from the local region of each frame, is not severely changed even with varying illuminations, To exploit the colour coherence as the features for formulating the background model is proposed. Experimental results on various benchmark databases show the efficiency and robustness of the proposed method compared to the previous approaches introduced in the literature.

LUIFT: LUminance Invariant Feature Transform

Illumination-invariant method for computing local feature points and descriptors, referred to as LUminance Invariant Feature Transform (LUIFT), is proposed. The method helps us to extract the most significant local features in images degraded by nonuniform illumination, geometric distortions, and heavy scene noise. The proposed method utilizes image phase information rather than intensity variations, as most of the state-of-the-art descriptors. Thus, the proposed method is robust to nonuniform illuminations and noise degradations. In this work, we first use the monogenic scale-space framework to compute the local phase, orientation, energy, and phase congruency from the image at different scales. Then, a modified Harris corner detector is applied to compute the feature points of the image using the monogenic signal components. The final descriptor is created from the histograms of oriented gradients of phase congruency. Computer simulation results show that the proposed method yields a superior feature detection and matching performance under illumination change, noise degradation, and slight geometric distortions comparing with that of the state-of-the-art descriptors.

OptiFuzz: a robust illumination invariant face recognition system and its implementation

Vision-based human face detection and recognition are widely used and have been shown to be effective in normal illumination conditions. Under severe illumination conditions, however, it is very challenging. In this paper, we address the effect of illumination on the face detection and the face recognition problem by introducing a novel illumination invariant method, called OptiFuzz. It is an optimized fuzzy-based illumination invariant method to solve the effect of illumination for photometric-based human face recognition. The rule of the Fuzzy Inference System is optimized by using a genetic algorithm. The Fuzzy’s output controls an illumination invariant model that is extended from Land’s reflectance model. We test our method by using Yale B Extended and CAS-PEAL face databases to represent the offline experiments, and several videos are recorded at our campus to represent the online indoor and outdoor experiments. Viola–Jones face detector and mutual subspace method are employed to handle the online face detection and face recognition experiments. Based on the experimental results, we can show that our algorithm outperforms the existing and the state-of-the-art methods in recognizing a specific person under variable lighting conditions with a significantly improved computation time. Other than that, using illumination invariant images is also effective in improving the face detection performance.

Detection and removal of shadow in still images using illumination invariant method

Shadow detection and removal is fundamental problem in computer graphics and computer vision communities, which can greatly improve the performance of various applications, such as image interpretation and object classification. Shadow removal is also beneficial to increase the visual realism and physical realism in image editing and processing. As a preprocess procedure, we present an automatic shadow detection method to obtain accurate shadow boundaries. Then based on the shadow detection results, we develop an efficient shadow removal method using illumination invari ant method to produce high-quality shadow-free image. Experimental results show that it can accurately detect the shadow regions in an image. In some cases, intensity of shadow matches with that of dark objects and it founds difficulty to correctly detect the shadow region due to shadings present in the images that of dark intensity objects. The algorithm works well on natural scene images and easily removes the shadow regions in them.

Phase Correlation based Local Illumination-invariant Method for Multi-Tempro Remote Sensing Image Matching

Abstract. This paper aims at image matching under significantly different illumination conditions, especially illumination angle changes, without prior knowledge of lighting conditions. We investigated the illumination impact on Phase Correlation (PC) matrix by mathematical derivation and from which, we decomposed PC matrix as the multiplication product of the illumination impact matrix and the translation matrix. Thus the robustness to illumination variation of the widely used Absolute Dirichlet Curve-fitting (AD-CF) algorithm for pixel-wise disparity estimation is proved. Further, an improved PC matching algorithm is proposed: Absolute Dirichlet SVD (AD-SVD), to achieve illumination invariant image alignment. Experiments of matching DEM simulated terrain shading images under very different illumination angles demonstrated that AD-SVD achieved 1/20 pixels accuracy for image alignment and it is nearly entirely invariant to daily and seasonal solar position variation. The AD-CF algorithm was tested for generating disparity map from multi-illumination angle stereo pairs and the results demonstrated high fidelity to the original DEM and the Normalised Correlation Coefficient (NCC) between the two is 0.96.