Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Annotating images is the most important task in creating AI applications. Datasets for computer vision models are generated through image annotation task in which training sets are used to train models, and test/validation sets are used to evaluate their performance. For functional datasets, labelling is necessary because it enables the training model to identify the important parts of the image (classes) so that it can identify those classes later on in new, previously undocumented images.Image Annotation can be done manually or with computer assistance. An entire image can be manually labelled or regions on an image can be drawn by humans.Manual annotation is a time consuming process and also it is prone to more errors.These limitations led to the growth of automatic image annotation.Automated image annotation involves assigning labels to digital images that describe the picture's
content in the best way..Automatic image annotation is a faster process and also results in greater accuracy compared to manual annotation process. It is possible to annotate images in several ways, but the most advanced way is through segmentation. The task of segmenting an image entails grouping together parts that share the same class of objects.Segmentation process involves assigning pixel to specific category to which they belong to. Different methods of segmentation can be utilized, but semantic
segmentation is the most intensive form of segmentation.The semantic segmentation technique is a deep pixel-by-pixel
classification technique, and a segmentation model is a special library that supports multiple architectures for semantic
segmentation.A review of different architectures used in the semantic segmentation process is presented in this paper in a broader perspective.
Keywords:
UNET, Semantic Segmentation, CNN
Cite Article:
"Literature Survey on Semantic Segmentation", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2455-2631, Vol.7, Issue 6, page no.1827 - 1829, June-2022, Available :http://www.ijrti.org/papers/IJRTI2206272.pdf
Downloads:
000205383
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator