Computers are greatly influencing the lives of human beings and their usage is increasing at arntremendous rate. The ease with which we can exchange information between user and computerrnis of immense importance today because input devices such as keyboard and mouse havernlimitations in comparison with input through natural handwriting. We can use the onlinernhandwriting recognition process for a quick and natural way of communication betweenrncomputer and human beings. Over the years, handwriting recognition is in research and hasrnattracted many researchers across the world. The main goal of this thesis is to develop an onlinernhandwritten Amharic word recognition system.rnIn this work, we present writer-independent HMM-based Amharic word recognition for onlinernhandwritten words. In our approach, the central idea is to build the HMM model for each word.rnThe underlying units of the recognition system are a set of primitive strokes whose combinationsrnform handwritten Amharic words. For each word, possibly occurring sequences of primitivernstrokes and their spatial relationships, collectively termed as primitive structural features, arernstored as feature list. In the training phase the extracted features of each word are used as featurernvectors which will be given as input parameters to each HMM model. In the case of recognition,rna model for each separated word is built up using the same approach. This model is used by thernsystem to perform the recognition using the Viterbi decoding algorithm. We also present arndataset collected for training and testing online recognition systems for Amharic words. Therndataset is prepared in accordance with the international standard UNIPEN format. Thernrecognition system is tested with the collected dataset and we achieved word recognition rates ofrn90.9% for numeral words and 73.94 % for other words. The overall recognition rate of thernsystem is 79.54% for all words in the dataset.rnKeywords: Handwriting recognition, Amharic word recognition, Online Recognition.