Blood vessels and optic disc (OD) detection is important in developing systems for automated diagnosis of various ophthalmic pathologies. This work proposes two efficient approaches for automatic detection of blood vessels and OD in retinal images. For extraction of blood vessels, first the Gabor filters are applied so as to enhance the contrast between the blood vessels and the background, and then, local entropy thresholding is applied for segmentation. The DRIVE database is used for comparative analysis. The average accuracy, sensitivity and specificity of proposed method are 93.85, 70.99 and 97.35%, respectively. The proposed technique produced better segmentation when compared with the existing algorithms. For localisation and detection of OD, a new histon-based algorithm is proposed in which roughness index of the histon and histogram is used for thresholding. The localised OD area is used as a mask, since it reduces execution time for segmentation of the OD. The proposed techniques have been tested over publicly available data-sets. The OD localisation accuracy for DRIVE and DIARETDB1 database is 95 and 91%, respectively.