Pixel classification in land scape images has been found to be challenging. The problem becomes more challenging in forest images due to the similar spectral features of pixels situated close to each other. Geographically weighted variables have been employed to classify the two different species namely Cryptomeria japonica (Japanese Cedar or Sugi) and Chamaecyparisobtusa (Japanese Cypress or Hinoki) and one mixed forest class. Previous attempts have shown reasonable improvement in this task using Genetic Algorithm supported Neural Network over other traditional approaches. Motivated by this, a NSGA-II supported Neural Network (NN-NSGA-II) classifier is proposed. The proposed model has been compared with GA-NN (ANN trained with Genetic Algorithm with a single objective function) classifiers in terms of confusion matrix based performance metrics such as accuracy, precision, recall and F-Measure. Experimental results have indicated that the proposed NN-NSGA-II model is superior to the GA-NN model to a greater extent. © 2017 IEEE.