Adaptive Image Enhancement Method for Object Recognition Based on Statistical Photometric Characteristics

A Hybrid Technique for Robust Object Detection for Identification of Classifying Objects

Object detection in real-world environments faces significant challenges from blur, noise, occlusion, and varying illumination, which degrade detection accuracy and robustness. This paper proposes an enhancement-assisted Faster R-CNN technique that integrates classical image restoration with deep learning to improve detection under degraded conditions. The method applies Wiener filtering to recover lost structural details, followed by adaptive histogram equalization for contrast restoration. Boundary box aware augmentation & optimized anchor estimation to improve localization exactness across diverse object scales during training. At inference, Soft-NMS and TTA enhance prediction stability in crowded scenes. The system is built on a ResNet-50 backbone within the Faster R-CNN architecture and is evaluated under three conditions: original, noisy & blurred images. Results demonstrate mAP improvement from 93.57% to 98.41%, a 3.5% increase in detection rate, and enhanced PSNR and SSIM scores. These findings confirm that integrating image restoration with optimized detection strategies significantly improves robustness without architectural modifications.

Consistent Photometric Enhancement Network for Remote Sensing Change Detection

Change detection performance in remote sensing is highly sensitive to illumination variations between bi-temporal images. In real-world scenarios, low-light conditions and inconsistent brightness often lead to degraded feature representations and unreliable detection results. To address this issue, this paper proposes a Consistent Photometric Enhancement Network (CPEN) for change detection under complex illumination conditions. Unlike conventional low-light enhancement methods applied independently to each image, CPEN explicitly enforces photometric consistency between bi-temporal images before and during an enhancement procedure. The proposed framework applies a low-light compensation mechanism to reduce photometric discrepancies between image pairs, which is followed by a bi-temporal enhancement module that jointly improves brightness while preserving shared structural information. Using the photometrically consistent and enhanced images, a change detection module is employed to extract reliable features and generate accurate change maps. Experimental results show that CPEN achieves F1/IoU scores of 90.39/82.67, 80.71/70.58, 78.34/64.26, and 86.26/79.02 on LEVIR-CD, PRCV-CD, SYSU-CD, and the real-world NPULL-CD dataset, respectively, demonstrating its robustness under both simulated and real illumination variations.

Adaptive enhancement algorithms of low-quality high-bit infrared-image based on multi-feature fusion and spectral mapping

Infrared images are widely used in the field of autonomous driving, which can effectively compensate for the deficiency of visible images under weak imaging conditions. The infrared images, generated in the autonomous driving field, are mostly 14-bit, high gray-scale ones that cannot be directly displayed on an ordinary 8-bit monitor. Therefore, an adaptive infrared image enhancement algorithm based on multi-feature fusion was firstly proposed to adaptively enhance the infrared images with uneven light and dark distribution. Secondly, to avoid physiological perceptual limitations of human vision for insufficient grayscale discrimination, a new pseudo-color enhancement algorithm for high-bit infrared-images based on spectral mapping was proposed. Finally, to improve adaptive level for the above pseudo-color enhancement problem, a priori luminance statistics method was proposed. The experimental results show that the proposed method can adaptively enhance infrared images with uneven light and dark distribution, with more coordinated enhancement effect, which has obvious advantages compared with other methods. The subjective and objective image quality evaluation indexes are better than those of most existing mainstream advanced algorithms, providing reliable technical support for applications in the related fields.

Universal low-light image restoration based on adaptive enhancement diffusion model

Adaptive Low-Light Image Enhancement Selection Using Random Forest: Validation on ExDark Dataset with BRISQUE Quality Assessment

Low-light image enhancement remains challenging for resource-constrained edge devices where deep learning models are often too computationally expensive. This research presents an adaptive selection framework that learns to choose between two complementary enhancement strategies—a lightweight logarithmic boost and a sophisticated realistic fusion method—based on image characteristics. A Random Forest classifier trained on 7 PCA-reduced features from 1,385 images achieves 86.1% accuracy for method selection, with 5-fold cross-validation confirming robust performance (84.3% ± 1.2%). This method is tested on ExDark dataset containing 1200 images from 12 classes. Object detection uses blur and image quality metrics (BRISQUE, NIQE, PIQE) along with YOLOv8. The results show clear differences, with a 2.1% improvement in detection rate (p = 0.017), a 10% improvement in BRISQUE quality (p < 0.001), and a 26.7% increase in brightness (p < 0.001). When combined with other methods, it leaves behind Histogram Smoothing (61.5%) and CLAHE (68.0%) and matches Gamma Correction (70.5%), but BRISQUE scores (21.93 and 26.78) make images look more natural. On closer inspection, certain categories such as bicycles show significant increases, but boats, bottles, and dining tables do not receive better detection scores. It shows clear scenarios where this approach works well and where it doesn’t. Additionally, this method takes up almost no space at just 1.86 MB and runs at 18.6 FPS on an average CPU without requiring any special graphics hardware. This makes it handy for edge devices like cameras or phones, especially in low light where sharpening edges and retaining detail is critical. The method is simple, requires little space and offers better results for certain classes without requiring large resources.

SFSNet: object detection in adverse weather via active frequency-spatial feature recovery