In this work we introduce Multi-Resolution Empirical Mode Decomposition (MREMD) as an image decomposition method that simplifies the implementation of Empirical Mode Decomposition (EMD) for bidimensional data. The proposed method is used in conjunction with the local binary pattern (LBP) to classify the images of six types of defects that can be found on the surface of rolled steel. The process starts by performing MREMD on the training images to obtain the first bidimensional intrinsic mode function (BIMF). Then features are extracted from the images and their first BIMF using the LBP. These features are used to train an artificial neural network (ANN) classifier. After training, given an unknown test image containing a defect, MREMD is applied on it to obtain its first BIMF. Next, LBP features are extracted from the image and its first BIMF and these features are fed to the trained ANN classifier to assign the image to one of the six defect classes. The classification process is carried out on 900 test images of the NEU database of six types of surface defects. The approach achieves an overall accuracy that is better than the result obtained using the LBP features alone. The main contribution of this paper is the introduction of multi resolution envelope interpolation using downsampling and upsampling with a fixed window size that reduces the execution time and decrease the sensitivity of the resulting BIMFs to the positions and number of extrema in the input image.

Skin cancer is the most common type of cancer in many parts of the world. As skin cancers start as skin lesions, it is important to identify precancerous skin lesions early. In this paper we propose an image based skin lesion identification to classify seven different classes of skin lesions. First, Multi Resolution Empirical Mode Decomposition (MREMD) is used to decompose each skin lesion image into a few Bidimensional intrinsic mode functions (BIMF). MREMD is a simplified bidimensional empirical mode decomposition (BEMD) that employs downsampling and upsampling (interpolation) in the upper and lower envelope formation to speed up the decomposition process. A few BIMFs are extracted from the image using MREMD. The next step is to locate the lesion or the region of interest (ROI) in the image using active contour. Then Local Binary Pattern (LBP) is applied to the ROI of the image and its first BIMF to extract a total of 512 texture features from the lesion area. In the training phase, texture features of seven different classes of skin lesions are used to train an Artificial Neural Network (ANN) classifier. Altogether, 490 images from HAM10000 dataset are used to train the ANN. Then the accuracy of the approach is evaluated using 315 test images that are different from the training images. The test images are taken from the same dataset and each test image contains one type of lesion from the seven types that are classified. From each test image, 512 texture features are extracted from the lesion area and introduced to the classifier to determine its class. The proposed method achieves an overall classification rate of 98.9%.