Many local texture features are proposed for texture classification and retrieval. Fuzzy Local Binary Pattern (FLBP) is one of such promising texture descriptor found in the literature. However, the fuzzification parameter (T) used in FLBP is computed empirically and not adaptive to local content. In addition, one need to perform several experiments over a large range of T to find its optimal value. In this paper a novel technique is proposed to compute fuzzification parameter and the resulting descriptor is named as Adaptive Fuzzy Local Binary Pattern (AFLBP). In the proposed technique, the computation of fuzzification parameter is adaptive in nature and thereby capture most representative feature for each pixel in the image. The earlier paper makes use of Support Vector Machine (that uses a non-linear kernel) to test the discriminating ability of the FLBP descriptor. Here, in this paper, the K-Nearest Neighbors (kNN) classifier is used as a classifier to investigate the discriminating strength of the proposed feature descriptor. The discriminating ability of the proposed texture descriptor is compared with that of local binary pattern (LBP) and fuzzy local binary pattern (FLBP) using Brodatz texture database. The result shows that the proposed descriptor outperforms other competing descriptors used in the experiment irrespective of the distance measure used for classification. It is also observed that the k-NN classifier using Manhattan distance outperforms all other combinations.