This article proposes a hybrid classifier for hyperspectral image(HSI) integrating the merits of two prominent classifiers: convolution neural network(CNN) and ensemble learning method. Both of them have evidence of efficient recognition capability of finding patterns from data. The ensemble model performs recognition using the salient features extracted by CNN. A modified version of Alexnet compatible with HSI datacube has been adopted as the CNN model. Three ensemble methods have been applied for recognition: adaptive boosting(adaboost), random forest(RF), and extreme gradient boosting(XGBoost). Two base learners have been used with adaboost: decision tree and support vector machine(SVM). Experiments have been performed on three benchmark datasets: Indian Pines,University of Pavia and Kennedy Space Centre, which mostly include land cover of agriculture, forest, soil, rural, and urban area. Experimental results establish the superiority of CNN with adaboosthybrid method where SVM is used as the base learner.