Concerning the high probability of mismatching and matching-loss that exists in traditional epipolar constraint matching algorithm, an algorithm based on similar image geometric features is proposed for binocular matching. The initial matching points which locate in the same or different epipolar lines are identified respectively using epipolar geometric constraint algorithm. According to the position similarity of matching points, maximum vector angle criterion and maximum angle difference criterion are derived. In order to match the points locat in different epipolar lines, utilizing disparity gradient limited constraint as well as maximum vector angle criterion, a mismatching elimination algorithm based on updating strategy is proposed, which can reduce the rate of mismatching and erroneous elimination. For the initial matching points locating in the same epipolar line, maximum angle difference and maximum vector angle criterion are used to extract candidate matching points. These candidate matching points are further examined, thus decreases the rate of matching-loss. Experimental results indicate that the algorithm has high matching accuracy and versatility. The incidence rate of mismatching and matching-loss can be controlled within 0.1% and 7%, respectively, and the algorithm is appropriate for objects with different structural complexity.