IRO Journals
Journal of Innovative Image Processing

Selective Image Enhancement for Robust GentleBoost Face Detection under Uncontrolled Illumination

Open Access
Published: 16 October, 2026
Pages: 1493-1508
  • Alyaa Qusay Aloraibi Alyaa Qusay Aloraibi
    Department of Artificial Intelligent, College of Computer Science and Mathematics, University of Mosul, Mosul, Iraq
    Department of Artificial Intelligent, College of Computer Science and Mathematics, University of Mosul, Mosul, Iraq
view PDF
view PDF

How to Cite

Aloraibi, Alyaa Qusay. 2026. “Selective Image Enhancement for Robust GentleBoost Face Detection under Uncontrolled Illumination”. Journal of Innovative Image Processing 8 (4): 1493-1508. https://doi.org/10.36548/jiip.2026.4.008.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Uncontrolled Illumination
CIELAB
CLAHE
Face Detection
GentleBoost
Cascade Classifier
LBPH

Abstract

Although significant progress has been achieved in computer vision, detecting faces under different lighting conditions and poses remains challenging. This issue is particularly crucial for biometric and surveillance applications, where lighting cannot be controlled. While the machine learning based Gentle Boost cascade provides stability benefits, it has not been studied extensively in face detection research. This paper introduces Selective Image Enhancement (SIE), a lightweight preprocessing technique designed to enhance image quality prior to detection. SIE operates on the (L) channel of the Commission Internationale de l'Éclairage CIELAB (LAB) color space, breaking down the (L) channel into illumination and detail components. It employs Gaussian filtering, gamma correction, and thresholding to selectively enhance image pixels while minimizing artifacts. Features are extracted using Local Binary Patterns Histogram (LBPH) and then classified with the Gentle Boost cascade, trained on the CelebA dataset and evaluated on 500 images. A comparative evaluation was conducted against gamma correction and Contrast Limited Adaptive Histogram Equalization (CLAHE). The proposed SIE method achieved 0.9800 recall, 0.9684 precision, and an F1-score value of 0.9742, with an average IoU of 0.7161 ± 0.0938. Although CLAHE achieved higher recall and F1-score value, SIE obtained the highest mean IoU among the evaluated enhancement methods. The unenhanced images achieved a slightly higher IoU of 0.7193 ±0.0926. These results indicate that SIE provides competitive detection performance and a balance between image enhancement quality and localization accuracy.

References

  1. Thaher, Thaer, Majdi Mafarja, Muhammed Saffarini, Abdul Hakim Mohamed, and Ayman El-Saleh. “A Comprehensive Review of Face Detection Techniques for Occluded Faces: Methods, Datasets, and Open Challenges.” (2025).
  2. Ariffin, Noor Afiza Mohd, Usman Abdul Gimba, and Ahmad Musa. “Face Detection Based on Haar Cascade and Convolution Neural Network (CNN).” Journal of Advanced Research in Computing and Applications 38, no. 1 (2025): 1-11.
  3. Viola, Paul, and Michael Jones. “Rapid Object Detection Using a Boosted Cascade of Simple Features.” In Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001, vol. 1, IEEE, 2001, I-I.
  4. Anab, Solomon, Godbless Mensah, Edward Yellakuor Baagyere, and Adamu Mustapha Mohammed. “An Enhanced LBPH Algorithm for Robust Face Feature Extraction.” Int. J. Multidisciplinary Res 6, no. 5 (2024): 27853.
  5. Wu, Ji, Bing Ding, Beining Zhang, and Jie Ding. “A Retinex-based Network for Image Enhancement in Low-Light Environments.” Plos one 19, no. 5 (2024): e0303696.
  6. Adeshina, Sirajdin Olagoke, Haidi Ibrahim, Soo Siang Teoh, and Seng Chun Hoo. “Custom Face Classification Model for Classroom Using Haar-like and LBP Features with their Performance Comparisons.” Electronics 10, no. 2 (2021): 102.
  7. Haq, Mahmood Ul, Muhammad Athar Javed Sethi, Sadique Ahmad, Naveed Ahmad, Muhammad Shahid Anwar, and Alpamis Kutlimuratov. “A Comprehensive Review of Face Detection/Recognition Algorithms and Competitive Datasets to Optimize Machine Vision.” Comput. Mater. Continua 84, no. 1 (2025): 1-24.
  8. Mamieva, Dilnoza, Akmalbek Bobomirzaevich Abdusalomov, Mukhriddin Mukhiddinov, and Taeg Keun Whangbo. “Improved Face Detection Method Via Learning Small Faces on Hard Images Based on a Deep Learning Approach.” Sensors 23, no. 1 (2023): 502.
  9. Friedman, Jerome, Trevor Hastie, and Robert Tibshirani. “Special Invited Paper. Additive Logistic Regression: A Statistical View of Boosting.” Annals of statistics (2000): 337-374.
  10. Lienhart, Rainer, Alexander Kuranov, and Vadim Pisarevsky. “Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection.” In Pattern Recognition, Berlin Heidelberg (2003): 297-304.
  11. Hien, Lam Thanh, Do Nang Toan, Ha Manh Toan, and Thanh-Lam Nguyen. “Effective Detection of Human Face with GentleBoost Approach.” International Journal of Computer Science and Network Security 16, no. 12 (2016): 103-108.
  12. Hbali, Youssef, Lahoucine Ballihi, Mohammed Sadgal, and El Fazziki Abdelaziz. “Face Detection for Augmented Reality Application Using Boosting-Based Techniques.” International Journal of Interactive Multimedia and Artificial Intelligence 4 no. 2 (2016):22–28.
  13. Yan, Chen, Zhengqun Wang, and Chunlin Xu. “Gentle Adaboost Algorithm Based on Multi‐feature Fusion for Face Detection.” The Journal of Engineering 2019, no.15 (2019): 609–12.
  14. Alsabry, Ayman, Malek Algabri, Amin Mohamed Ahsan, Mogeeb A. A. Mosleh, F. E. Hanash, and Hamzah Ali Abdulrahman Qasem. “An Optimal Framework Based on the GentleBoost Algorithm and Bayesian Optimization for the Prediction of Breast Cancer Patients’ Survivability.” International Journal of Computing 23, no. 1(2024): 85–93.
  15. Siu, Chapman. “Online GentleAdaBoost -- Technical Report.” arXiv Preprint, arXiv 2308.14004: (2023).
  16. Zhang, Na. “A Study on the Impact of Face Image Quality on Face Recognition in the Wild.” arXiv Preprint, arXiv:2307.02679 (2023).
  17. Zhang, Wanli, Xianwei Li, Qixiang Song, and Wei Lu. “A Face Detection Method Based on Image Processing and Improved Adaptive Boosting Algorithm.” Traitement Du Signal 37, no. 3 (2020): 395–403.
  18. Chatisa, Ivan, Siti Syahidatul Helma, and Ibnu Surya. “Analysis of Illumination Invariant Method for Face Detection in Different Lighting Variations.” Journal of Applied Informatics and Computing 10, no. 3 (2026): 2568–78.
  19. Fradejas, Dayne, Vince Harley Gaba, Analyn Yumang, and Ericson Dimaunahan. “Enhancing the Haar Cascade Algorithm for Robust Detection of Facial Features in Complex Conditions Using Area Analysis and Adaptive Thresholding.” Engineering Proceedings 107, no. 1 (2025): 3.
  20. Saryanto, Saryanto, and Widyastuti Andriyani. “Gaussian Blur Filter Effect Analysis on Facial Detection Accuracy Using Viola Jones Method.” IJCCS (Indonesian Journal of Computing and Cybernetics Systems) 18, no. 3 (2024): 1-12.
  21. Liu, Ziwei, Ping Luo, Xiaogang Wang, and Xiaoou Tang. “Deep Learning Face Attributes in the Wild.” In Proceedings of the IEEE international conference on computer vision (2015): 3730-3738.
  22. Huang, Gary B., Marwan Mattar, Tamara Berg, and Eric Learned-Miller. “Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments.” Workshop on Faces in 'Real-Life'” Images: Detection, Alignment, and Recognition (2008): 1–14.
  23. Muratbekova, Muragul, Nuray Toganas, Ayan Igali, et al. “Color Models in Image Processing: A Review and Experimental Comparison.” Discover Applied Sciences 8, no. 5 (2026): 494.
  24. Moradzadeh, Sadeq, and Vahid Mehrdad. “Improvement of Medical Images with Multi-Objective Genetic Algorithm and Adaptive Morphological Transformations.” Scientific Reports 15, no. 1 (2025): 24167.
  25. Padilla, Rafael, Wesley L. Passos, Thadeu L. B. Dias, Sergio L. Netto, and Eduardo A. B. Da Silva. “A Comparative Analysis of Object Detection Metrics with a Companion Open-Source Toolkit.” Electronics 10, no. 3 (2021): 279.