Abstract Deep learning is one of the trending technologies in computer vision to identify and classify objects. Deep learning is a subset of Machine Learning and Artificial Intelligence. Detecting and classifying the object was a challenging task in traditional computer vision techniques, and now there are numerous deep learning techniques scaled up to achieve this. The primary purpose of the research is to detect and segment the human hand wrist region using deep learning methods. This research is widespread to deep learning enthusiasts who needs to segment custom objects using instance segmentation. We demonstrated a segmented hand wrist using the Mask Regional Convolutional Neural Network (R-CNN) technique with an average accuracy of 99.73%. This work also compares the performance evaluation of baseline and custom Hand Wrist Mask R- CNN. The achieved validation class loss is 0.00866 training and 0.02736 validation; both the values are comparatively deficient compared with baseline Mask R-CNN.

References

[1] Ahmad R., Naz S., Afzal M., Rashid S., Liwicki M., and Dengel A., “A Deep Learning based Arabic Script Recognition System: Benchmark on KHAT” The International Arab Journal of Information Technology, vol. 17, no. 3, pp. 299- 305, 2020.

[2] Amin A. and Qureshi M., “A Novel Image Retrieval Technique using Automatic and Interactive Segmentation,” The International Arab Journal of Information Technology, vol. 17, no. 3, pp. 404-410, 2020.

[3] Badruswamy S., “Evaluating Mask R-CNN Performance for Indoor Scene Understanding,” 2018.

[4] Bhukya R. and Ashok A., “Gene Expression Prediction Using Deep Neural Networks,” The International Arab Journal of Information Technology, vol. 17, no. 3, pp. 422-431, 2020.

[5] Cai L., Long T., Dai Y., and Huang Y., “Mask R- CNN-Based Detection and Segmentation for Pulmonary Nodule 3D Visualization Diagnosis,” IEEE Access, vol. 8, pp. 44400-44409, 2020,

[6] Ganesh P., Volle K., Burks T., and Mehta S., “Deep Orange: Mask R-CNN based Orange Detection and Segmentation,” ELSEVIER IFAC International Federation of Automatic Control, vol. 52, no. 30, pp. 70-75, 2019.

[7] Garcia-Garcia A., Orts-Escolano S., Oprea S., Villena-Martinez V., and Garcia-Rodriguez J., “A Review on Deep Learning Techniques Applied to Semantic Segmentation,” arXiv:1704.06857v1, 2017.

[8] Girshick R., “Fast R-CNN,” arXiv:1504.08083v2, 2015.

[9] Girshick R., Donahue J., Darrell T., and Malik J., “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation,” arXiv:1311.2524v5, 2014.

[10] GokulaKrishnan E. and Malathi G., “A Survey on Multi-feature Hand Biometrics Recognition,” in Proceeding of Computational Vision and Bio Inspired Computing, pp. 1061-1071, 2018.

[11] GokulaKrishnan E. and Malathi G., “Contactless Novel Hand Wrist Biometrics Feature Extraction using SURF,” International Journal of Civil Engineering and Technology, vol. 9, no. 11, pp. 1102-1114, 2018.

[12] He K., Gkioxari G., Dollar P., and Girshick R., “Mask R-CNN,” arXiv:1703.06870v3, 2018.

[13] Hu Q., Souza L., and Holanda G., Alves S., Silva F., Han T., and Filho P., “An Effective Approach for CT Lung Segmentation using Mask Region- based Convolutional Neural Networks,” Artificial Intelligence in Medicine, vol. 103, pp. 101792, 2020.

[14] Inoue K., “Semantic Segmentation of Breast Lesion Using Deep Learning,” Ultrasound in Medicine and Biology, vol. 45, pp. S52, 2019.

[15] Issac A., Manohar H., and Jain V., “Segmentation for Complex Background Images using Deep Learning Techniques,” International Journal of Recent Technology and Engineering, vol. 8, no. 2, pp. 1746-1750, 2019.

[16] Jian S., Kaiming H., Ross G., and Shaoqing R., “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” arXiv:1506.01497v3, 2016.

[17] Kopelowitz E. and Engelhard G., “Lung Nodules Detection and Segmentation Using 3D Mask- RCNN,” arXiv:1907.07676v6, 2019.

[18] Lin C. and Li Y., “A License Plate Recognition System for Severe Tilt Angles Using Mask R- CNN,” in Proceeding of International Conference on Advanced Mechantronic Systems, Kusatsu, pp. 229-234, 2019.

[19] Malathi G. and Shanthi V., “Statistical Measurement of Ultrasound Placenta Images Complicated by Gestational Diabetes Mellitus Using Segmented Approach,” International Conference on Signal and Image Processing, vol. 2, no. 4, pp. 332-343, 2011.

[20] Minaee S., and Boykov Y., Porikli F., Plaza A., Kehtarnavaz N., and Terzopoulos D., “Image Segmentation Using Deep Learning: A Survey,” arXiv:2001.05566v4, 2020.

[21] Pech-Pacheco J., Cristobal G., Chamorro- Martinez J., and Fernandez-Valdivia J., “Diatom Autofocusing in Brightfield Microscopy: A Comparative Study,” in Proceedings of 15th International Conference on Pattern Recognition, Barcelona, pp. 314-317, 2000.

[22] Qiao y., Truman M., and Sukkarieh S., “Cattle Segmentation and Contour Extraction Based on Mask R-CNN for Precision Livestock Farming,” Computers and Electronics in Agriculture, vol. 165, pp. 104958, 2019.

[23] Sen B. and Venugopal V., “Efficient Classification of Breast Lesion based on Deep Learning Technique,” Bonfring International Journal of Advances in Image Processing, vol. 6, no. 1, pp. 1-6, 2016.

[24] Tabash B., Abd-Allah M., and Tawfik B., “Intrusion Detection Model Using Naive Bayes and Deep Learning Technique,” The International Arab Journal of Information Technology, vol. 17, no. 2, pp. 215- 224, 2020.

[25] Yu Y., Zhang K., Yang L., Zhang D., and Kailiang Z., “Fruit Detection for Strawberry Harvesting Robot in Non-Structural Environment based on Mask-RCNN,” Computers and Electronics in Agriculture, vol. 163, pp. 104846, 2019. 792 The International Arab Journal of Information Technology, Vol. 19, No. 5, September 2022

[26] Zhao T., Yang Y., Niu H., Wang D., and Chen Y., “Comparing U-Net Convolutional Network with Mask R-CNN in the Performances of Pomegranate Tree Canopy Segmentation,” in Proceeding of SPIE, Multispectral, Hyperspectral and Ultraspectral Remote Sensing Technology, Techniques and Application, Honolulu, 2018. GokulaKrishnan Elumalai is currently pursuing Ph.D. research scholar in Computer Science and Engineering from Vellore Institute of Technology, Chennai, Tamilnadu, India. His research interest includes Computer Vision, Deep Learning, Biometrics, and Artificial Intelligence. He filed a patent on his research areas on novel Biometrics. Malathi Ganesan is working as a Professor in the School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, Tamil Nadu, India. She has over 20 years of experience in teaching and research. Her area of specialization is Image Processing and Healthcare Analytics. She has been a resource person in FDPs, workshops, and Seminars. Currently, she is guiding 3 Ph.D. scholars and has several publications in reputed International Journals. She has authored a few book chapters. She has filed a patent in novel Biometrics. She received Best Outstanding Faculty Award in Computer Science ‘by VENUS Foundation in July 2018.