These days research in Optical Character Recognition is popular for its application potentialrnin banks, post offices, insurance, and other governmental and non-governmentalrnorganizations. Other application areas include library automation and natural languagernprocessing.rnAs Amharic is the working language of Ethiopia and used as a means of communication byrnmost governmental and non-governmental organizations, there is a huge collection ofrndocument and processing that could benefit from OCR system. To this end, since recentrntimes, research in the area of Amharic OCR system has been undertaken at SISA. Thernpresent research is a continuation with the aim of improving the performance of the systemrnunder investigation at SISA in recognizing characters written in different font types.rnTo this end, feature-based approach was considered after thoroughly studying features ofrnAmharic characters. Algorithms for thinning and feature extractions were reviewed fromrnliterature. An attempt was made to implement some of these algorithms so as to see theirrnperformance on Amharic text printed in different typeface s. Previous algorithmsrnimplemented for segmentation (stage-by-stage segmentation) and featurernextraction/detection (tree-based topological features extraction teclmique) are incorporatedrnwith some modification to complete the Amharic OCR. The system is then tested on samplernAmharic documents of actual cases (written in Agafari, Washra and Visual Geez) and testrnresults obtained for each of the case is repOt1ed. Recommendations are also drawn tornhighlight areas of further research so as to improve the current work and incorporate otherrnfeatures to Amharic OCR system.