Automatic feature localisation with constrained local models

• Published in: Pattern recognition Vol. 41; no. 10; pp. 3054 - 3067
• Main Authors: Cristinacce, David, Cootes, Tim
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.10.2008; Elsevier Science
• Subjects: Active appearance models; Applied sciences; Artificial intelligence; Biological and medical sciences; Computer science; control theory; systems; Computerized, statistical medical data processing and models in biomedicine; Constrained local models; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; Face detection; Feature detectors; Image processing; Information, signal and communications theory; Medical management aid. Diagnosis aid; Medical sciences; Object detection; Object localisation; Pattern recognition. Digital image processing. Computational geometry; Shape modelling; Signal and communications theory; Signal processing; Signal, noise; Telecommunications and information theory; Europe; Object localisation; Feature detectors; Shape modelling; Object detection; Active appearance models; Constrained local models; Face detection; Biometrics; Performance evaluation; Parameter estimation; Image processing; Video signal; Updating; Iterative method; Active appearance model; Modeling; Image reconstruction; Learning; Accuracy; Image sequence; Fixed image; Target detection; Object location; Computer vision; Target tracking; Range finding; Face recognition; Pattern recognition; Nuclear magnetic resonance imaging; Search algorithm; Medical imagery; Automatic recognition
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2008.01.024

We present an efficient and robust method of locating a set of feature points in an object of interest. From a training set we construct a joint model of the appearance of each feature together with their relative positions. The model is fitted to an unseen image in an iterative manner by generating templates using the joint model and the current parameter estimates, correlating the templates with the target image to generate response images and optimising the shape parameters so as to maximise the sum of responses. The appearance model is similar to that used in the Active Appearance Models (AAM) [T.F. Cootes, G.J. Edwards, C.J. Taylor, Active appearance models, in: Proceedings of the 5th European Conference on Computer Vision 1998, vol. 2, Freiburg, Germany, 1998.]. However in our approach the appearance model is used to generate likely feature templates, instead of trying to approximate the image pixels directly. We show that when applied to a wide range of data sets, our Constrained Local Model (CLM) algorithm is more robust and more accurate than the AAM search method, which relies on the image reconstruction error to update the model parameters. We demonstrate improved localisation accuracy on photographs of human faces, magnetic resonance (MR) images of the brain and a set of dental panoramic tomograms. We also show improved tracking performance on a challenging set of in car video sequences.