Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Automatic Human Face Detection for Content-based Image Annotation

Richard M. Jiang, Abdul H. Sadka, Huiyu Zhou


In this paper, an automatic human face detection approach using colour analysis is applied for content-based image annotation. In the face detection, the probable face region is detected by adaptive boosting algorithm, and then combined with a colour filtering classifier to enhance the accuracy in face detection. The initial experimental benchmark shows the proposed scheme can be efficiently applied for image annotation with higher fidelity.


Content-based image annotation has recently attracted a lot of interest from the research community, mainly due to the development of interactive multimedia technology over internet, wireless multimedia communication, and digital media broadcasting. In content-based image annotation, image analysis is the primary step to extract useful information from image databases. The difficulty in content-based image retrieval is how to summarize the low-level features into high-level or semantic descriptors to facilitate the retrieval procedure. Such a shift toward semantic visual data mining paradigm thus generates an urgent need to bridge the low level features with semantic understanding of the observed visual information.

To solve such a semantic gap problem , an efficient way is to develop a number of classifiers to identify the presence of semantic image components that can be connected to semantic descriptors. Among various semantic objects, human face is a very important semantic content , which is usually also the most concerned centric element in many images and photos. , the presence of faces can usually be correlated to specific scenes with semantic inference according to a given ontology. Therefore, face detection can be an efficient tool to annotate images for semantic descriptors.

Face detection seems extremely easy for the human visual system. However, it is still a complex problem in computer-based systems. The difficulty resides in the fact that faces are non rigid objects. Face appearance may vary between two different persons but also between two photographs of the same person, depending on the light conditions, the emotional state of the subject and pose. Faces also vary apparently with added features, such as glasses, hat, moustache beards and hair style.

Colour based approach has been developed for face detection as an intuitive and efficient approach. In comparison with geometric feature-based approach, detection algorithms using holistic representations have the advantage of finding small faces, pose-variant faces, or faces in poor-quality images . A combination of holistic and feature-based approaches is a promising approach to face detection. However, the colour-based approach face difficulties in robustly detecting skin colours in the presence of complex background and different lighting conditions . Jain proposed a robust face detection algorithm by combining holistic features with geometry features and semantic facial component maps of eyes, mouth using a parametric ellipse. Aachen (RWTH) combines face colour approach with principle component analysis (PCA) to achieve a high reliability in face detection. MIT also exploit colour cues for face recognition while shape cues are degraded.

for more details, please visit


Important Note..!

If you are not satisfied with above reply ,..Please


So that we will collect data for you and will made reply to the request....OR try below "QUICK REPLY" box to add a reply to this page
Popular Searches: content based image retrieval system by annotation ppt, automatic annotation to face image matlab, soil moisture content based automatic motor control for irrigation soil moisture content based automatic motor control for ir, content based image annotation matlab, image face annotation coding in matlab, automatic face annotation coding in matalab, automatic face annotation by mining the web pdf,

Forum Jump:

Users browsing this thread: 1 Guest(s)