Nowadays, digital photography is a common technology for capturing and archiving images due to the decreased costs for multimedia recording and storage devices, high transmission rates, and improved compression techniques, the digital image collections have grown rapidly in recent years. Annotation is considered as a pre-stage of the retrieval process. Image annotation, also known as image tagging, is a process by which labels or tags are associated with images, either manually, automatically or semi-automatically.
Manual image annotation is time-consuming, laborious and expensive; so, there has been a large amount of research done on automatic image annotation and retrieval technologies are combined to improve the performance. A computer system automatically assigns metadata in the form of text description or keywords to a digital image are called automatic image annotation.
An automatic image annotation and retrieval model is developed base on the intensity invariant approach. The system applied various preprocessing steps such as Gray scale converting, Noise filtering for image enhancing. In image segmentation, the system segment particular image according to their color intensity.
Some segmented images
In feature extraction, it extracts individual objects and assign associated words for each object to form training images. After feature extraction, each object is compared with annotated dataset to assign words and images respectively. The fabric and un-fabric images are applied for training and testing. The top words are described for annotated image in result.
- May The Yu and Myint Myint Sein, "Automatic image captioning system using integration of N-cut and color-based segmentation method", Proceedings of the International Conference on international conference on Instrumentation, Control, Information Technology and System Integration, Japan, September 13-18,. 2011.[pdf]
- May The Yu and Myint Myint Sein, "Automatic Image Annotation and Retrieval", Proceedings of the Ninth International Conference on Computer Application, May5-6, Myanmar, 2011.[pdf]