This study aims to calculate eyelid area to classify eye condition become awake or drowsy as the initial stage of a drowsiness detection system. This work used 40x95 matrix of 500 single eye images from 4 respondents. The input image will be processed into brightness enhancement, grayscaling, thresholding and eyelid area measurement. The problem of thresholding process was to determine the optimal threshold value that can be used on images with different intensities. Brightness enhancement modification is proposed to equalize the intensity histogram value of the input image based on the reference image. Threshold value based on this modification can be used as optimal threshold value. With this optimal threshold value, the eye condition classification results show that average accuracy achieved 93.5%.