Mammography uses mild doses of X-ray for capturing internal structure of breast for detection of tumors. Automation of mammogram type classification helps the doctor to take decisions more effectively. An improved AdaBoost classifier is proposed in this paper. Wavelet decomposition and Singular Value Decomposition (SVD) are used for feature extraction and reduction respectively. A novel hybrid learning Artificial Bee-AdaBoost (AB-AB algorithm) is proposed by combining concept of Artificial Bee Colony (ABC) algorithm and AdaBoost algorithm to improve the classification accuracy. The proposed algorithm is evaluated using the publicly available MIAS dataset. Experimental results show performance improvement of the proposed framework. © 2017 Elsevier B.V., All rights reserved.