Saini, Anu, Tripathi, Jyoti. (1400). Mapping Grayscale Images to Colour Space Using Deep Learning. , 14(Special Issue: Security and Resource Management challenges for Internet of Things), 52-68. doi: 10.22059/jitm.2022.85649
Anu Saini; Jyoti Tripathi. "Mapping Grayscale Images to Colour Space Using Deep Learning". , 14, Special Issue: Security and Resource Management challenges for Internet of Things, 1400, 52-68. doi: 10.22059/jitm.2022.85649
Saini, Anu, Tripathi, Jyoti. (1400). 'Mapping Grayscale Images to Colour Space Using Deep Learning', , 14(Special Issue: Security and Resource Management challenges for Internet of Things), pp. 52-68. doi: 10.22059/jitm.2022.85649
Saini, Anu, Tripathi, Jyoti. Mapping Grayscale Images to Colour Space Using Deep Learning. , 1400; 14(Special Issue: Security and Resource Management challenges for Internet of Things): 52-68. doi: 10.22059/jitm.2022.85649

Mapping Grayscale Images to Colour Space Using Deep Learning

Journal of Information Technology Management
دوره 14، Special Issue: Security and Resource Management challenges for Internet of Things، 2022، صفحه 52-68    اصل مقاله (1.5 M)
نوع مقاله: Research Paper
شناسه دیجیتال (DOI): 10.22059/jitm.2022.85649
نویسندگان
Anu Saini* 1؛ Jyoti Tripathi2
1Assistant Professor, Ph.D., Department of Computer Science and Engineering, G. B. Pant Govt. Engineering College, New Delhi, India.
2Assistant Professor, Department of Computer Science and Engineering, G.B. Pant Govt. Engineering College, New Delhi, India.
چکیده
People are used to exploring grayscale images in their family albums but it is difficult to grasp the reality without colours. Luckily, with advancements in Machine Learning it has been possible to solve problems previously thought impossible. The authors aim to automatically colourize grayscale images using a subset of Machine Learning called Deep Learning. The system will be trained on an image dataset and given an input grayscale image the model will be able to assign aesthetically believable colours. A grayscale photograph has been provided; our approach solves the problem of visualizing a reasonable colour version of the grayscale picture. This issue is undoubtedly under controlled; therefore earlier methods to this problem have either counted majorly on user interaction or it leads to in unsaturated colourizations. The authors put forward a completely automatic approach that will try to produce realistic and vibrant colourizations as much as possible. The proposed system has been applied as a feed-forward in a Convolutional Neural Network and has been trained on over twenty thousand colour images currently.
کلیدواژه‌ها
Convolutional Neural Networks (CNN)؛ Convolution؛ RGB؛ CIELAB (Lab)؛ Deep Neural Networks؛ Feature vector؛ Prediction؛ Sampling
مراجع
آمار
تعداد مشاهده مقاله: 1,251
تعداد دریافت فایل اصل مقاله: 1,042