Simple Global Thresholding Neural Network for Shadow Detection

Advances in digital technologies have allowed us to generate more images than ever. Images of scanned documents are examples of these images that form a vital part in digital libraries and archives. Scanned degraded documents contain background noise and varying contrast and illumination, therefore, document image binarisation must be performed in order to separate foreground from background layers. Image binarisation is performed using either local adaptive thresholding or global thresholding; with local thresholding being generally considered as more successful. This paper presents a novel method to global thresholding, where a neural network is trained using local threshold values of an image in order to determine an optimum global threshold value which is used to binarise the whole image. The proposed method is compared with five local thresholding methods, and the experimental results indicate that our method is computationally cost-effective and capable of binarising scanned degraded documents with superior results.

Download Full-text

End-to-End Neural Network for Shadow Detection using Combined Color Spaces

2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS) ◽

10.1109/iciccs48265.2020.9121088 ◽

2020 ◽

Author(s):

Shailender Kumar ◽

Dhruv Ramdev ◽

Himanshu Aggarwal ◽

Himanshu Choudhary

Keyword(s):

Neural Network ◽

Shadow Detection ◽

Color Spaces ◽

End To End

Download Full-text

Shadow Detection in Single RGB Images Using a Context Preserver Convolutional Neural Network Trained by Multiple Adversarial Examples

IEEE Transactions on Image Processing ◽

10.1109/tip.2019.2904267 ◽

2019 ◽

Vol 28 (8) ◽

pp. 4117-4129 ◽

Cited By ~ 4

Author(s):

Sorour Mohajerani ◽

Parvaneh Saeedi

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Shadow Detection ◽

Adversarial Examples ◽

Rgb Images

Download Full-text

TPUnit neural network and simple ensemble for abnormal shadow detection in lung X-ray images

2012 International Symposium on Intelligent Signal Processing and Communications Systems ◽

10.1109/ispacs.2012.6473497 ◽

2012 ◽

Author(s):

Asumi Ikeda ◽

Hiroki Yosimura ◽

Maiya Hori ◽

Tadaaki Shimizu ◽

Yoshio Iwai ◽

...

Keyword(s):

Neural Network ◽

Shadow Detection ◽

X Ray ◽

Abnormal Shadow

Download Full-text

Shadow Detection and Removal Technique using CNN

International Journal for Research in Applied Science and Engineering Technology ◽

10.22214/ijraset.2021.37667 ◽

2021 ◽

Vol 9 (8) ◽

pp. 1748-1755

Author(s):

Akanksha Bankhele

Keyword(s):

Neural Network ◽

Surveillance System ◽

Shadow Detection ◽

Loss Functions ◽

Surveillance Systems ◽

Traffic Surveillance ◽

Real World Applications ◽

Computer Vision Applications ◽

Actual Target ◽

Removal Technique

Abstract: The Shadow detection and removal Technique is used in many real-world applications, such as surveillance systems, computer vision applications and indoor outdoor system. The shape and orientation of an object, as well as the light source, can be revealed by shadows in an image. In a traffic surveillance system, the shadow can misclassify the actual target, lowering the system’s accuracy. Numerous algorithms and techniques have been developed by researchers to aid in the detection and removal of shadows in images. This paper aims to provide an overview of different shadow detection and removal techniques, their advantages and drawbacks. Also implementation of Convolutional Neural Network for shadow detection and OpenCV features to remove shadows by re-designing the output and analysing different loss functions to train the network. Keywords: Shadow Detection and Removal Techniques, Shadow Image Processing.

Download Full-text