Mohammad Ayache*, Mohamad Khalil**, Francois Tranquart***

*Faculty of Engineering, Biomedical Department. Islamic University of Lebanon, BP 30014, Highway Khalde,Lebanon

**Faculty of Engineering, Lebanese university, Beirut, Lebanon

***Faculty of Medicine, University of Tours, France

 Abstract
The aim of our study is to propose an approach for recognition of placental tissues using ultrasound images. This approach is based to the selection of tissues, feature extraction by wavelet transform and recognition of tissues by neural network and especially the multi layer perceptron MLP. The method is tested for ultrasound placental images; resulting in 95% success rate. The proposed approach showed a good recognition for placental tissues and will be useful for detection of the placental anomalies those concerning the premature birth and the intrauterine growth retardation.

Keywords: Placenta, wavelet transform, Neural network, MLP.