Visibility and Distortion Measurement for No-Reference Dehazed Image Quality Assessment via Complex Contourlet Transform

Abstract

Recently, most dehazed image quality assessment (DQA) methods have focused on estimating remaining haze and omitting distortion impact from the side effect of dehazing algorithms, which leads to their limited performance. Addressing this problem, we propose a method for learning both visibility and distortion-aware features no-reference (NR) dehazed image quality assessment (VDA-DQA). Visibility-aware features are exploited to characterize clarity optimization after dehazing, including the brightness-, contrast-, and sharpness-aware features extracted by the complex contourlet transform (CCT). Then, distortion-aware features are employed to measure the distortion artifacts of images, including the normalized histogram of the local binary pattern (LBP) from the reconstructed dehazed image and the statistics of the CCT subbands corresponding to the chroma and saturation map. Finally, all the above features are mapped into quality scores by support vector regression (SVR). Extensive experimental results on six public DQA datasets verify the superiority of the proposed VDA-DQA method in terms of consistency with subjective visual perception and outperform state-of-the-art methods. The source code of VDA-DQA is available at https://github.com/li181119/VDA-DQA.

Advancing Real-world Image Dehazing: A Comprehensive Dataset and Evaluation Metrics

“…A regressor then maps the 17 features into a quality score. VDA-DQA [17] estimates the quality of dehazing images by measuring visibility and distortions. An SVR model is used to map perceptual features into quality scores.…”

“…Additionally, we take into account three NR-DIQA metrics, namely BDQM [32], FADE [10], and VDA-DQA [17]. Unlike FID, these three metrics have been trained on datasets for DIQA, they do not require a reference image set, and predict a score for each individual image.…”

“…The perceived quality of MADIQA images is assessed through a subjective study. Participants are told to evaluate the overall image quality but also four aspects including presence of artifacts, Table 3 Comparison of the considered dehazing methods in terms of FID [19], FADE [10], VDA-DQA [17], and BDQM [32] on the URHID test set. Best and second best SID methods are highlighted in bold and underlined, respectively.…”

Exploring Maritime Search and Rescue Resource Allocation via an Enhanced Particle Swarm Optimization Method

“…In this way, the rescue operation can be performed in a more efficient manner when an accident happens, thus significantly reducing potential losses caused by the accident [11]. Many studies have been conducted to identify optimal path planning and facility distribution scenarios to minimize the total overhead (i.e., total traveling distance, time cost) in SAR activities [12][13][14]. It is found that the problem of optimizing SAR resource distribution can be formulated as a discrete location optimization problem.…”