Improved illumination invariant homomorphic filtering using the dual tree complex wavelet transform

Hill, Paul; Bhaskar, Harish; Al-Mualla, M.E.; Bull, David

doi:10.1109/icassp.2016.7471869

Cited by 4 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this, Butterworth's high pass filter was used. The homomorphic filter reduces inconsistency in the background illumination [22], making image segmentation easier. The image is then passed through a median filter to remove any salt and pepper noise [23].…”

Section: Figure 1 Block Diagram Of the Proposed Systemmentioning

confidence: 99%

Role of Deep Learning in Improving the Performance of Driver Fatigue Alert System

Fouad¹,

Labib²

2022

View full text Add to dashboard Cite

Driver fatigue detection system aims to monitor the driver state. When detecting a fatigue caused by different attitudes other than normal driving habit, the system warns the driver that traveling should be interrupted. In this way, it helps the driver to make the right decision. The aim of this study is to prevent traffic accidents. The system analyzes any changes in the driver's eyes and mouth features in real time and warns the driver when necessary. The proposed system contains several stages to detect the driver's fatigue. First, the preprocessing stage; enhancement of the frames, determining the face, and cropping eyes and mouth of the driver was done. Then, dealing with feature extraction stage; the features concerning each frame was processed. Finally, two classification approaches were presented and a comparison between them was addressed. In the first approach, four traditional classifiers were applied; Diagonal Linear Discriminant Analysis (DiagLDA), Linear Support Vector Machine (LSVM), K-Nearest Neighbor (KNN), and Random Forest Classifier (RFC). The results show that two classifiers; KNN and RFC yield the highest average accuracy of 91.94% for all subjects presented in this paper. In the second approach, one model of deep learning neural network (CNN) was applied; "Resnet-50" model. The results also show that the proposed deep learning model yields a high average accuracy of 96.3889% for the same data. In general, the drowsiness and lost focus of drivers with high accuracy have been detected with the developed image processing based system, which makes it practicable and reliable for real-time applications.

show abstract

Section: Figure 1 Block Diagram Of the Proposed Systemmentioning

confidence: 99%

Role of Deep Learning in Improving the Performance of Driver Fatigue Alert System

Fouad¹,

Labib²

2022

View full text Add to dashboard Cite

show abstract

“…The census transform was introduced to compute the visual correspondence based on intensity comparisons [ 33 , 34 ]. For tolerance to illumination variation, the local binary pattern operator and its extensions have been investigated [ 35 ] to construct order-based features for each pixel by comparing the intensity of pixels with that of adjacent pixels. The ordinal spatial intensity distribution [ 36 ] was constructed by ordering the pixel intensities in both the ordinal and spatial spaces.…”

Section: Related Workmentioning

confidence: 99%

A Spatial-Frequency Domain Associated Image-Optimization Method for Illumination-Robust Image Matching

Liu

Jia

et al. 2020

Sensors

View full text Add to dashboard Cite

Image matching forms an essential means of data association for computer vision, photogrammetry and remote sensing. The quality of image matching is heavily dependent on image details and naturalness. However, complex illuminations, denoting extreme and changing illuminations, are inevitable in real scenarios, and seriously deteriorate image matching performance due to their significant influence on the image naturalness and details. In this paper, a spatial-frequency domain associated image-optimization method, comprising two main models, is specially designed for improving image matching with complex illuminations. First, an adaptive luminance equalization is implemented in the spatial domain to reduce radiometric variations, instead of removing all illumination components. Second, a frequency domain analysis-based feature-enhancement model is proposed to enhance image features while preserving image naturalness and restraining over-enhancement. The proposed method associates the advantages of the spatial and frequency domain analyses to complete illumination equalization, feature enhancement and naturalness preservation, and thus acquiring the optimized images that are robust to the complex illuminations. More importantly, our method is generic and can be embedded in most image-matching schemes to improve image matching. The proposed method was evaluated on two different datasets and compared with four other state-of-the-art methods. The experimental results indicate that the proposed method outperforms other methods under complex illuminations, in both matching performances and practical applications such as structure from motion and multi-view stereo.

show abstract

Skin cancer detection and classification

Dubai

Bhatt

Joglekar

et al. 2017

2017 6th International Conference on Electrical Engineering and Informatics (ICEEI)

View full text Add to dashboard Cite

Improved illumination invariant homomorphic filtering using the dual tree complex wavelet transform

Cited by 4 publications

References 14 publications

Role of Deep Learning in Improving the Performance of Driver Fatigue Alert System

Role of Deep Learning in Improving the Performance of Driver Fatigue Alert System

A Spatial-Frequency Domain Associated Image-Optimization Method for Illumination-Robust Image Matching

Skin cancer detection and classification

Contact Info

Product

Resources

About