Object detection and image cropping using a multi-detector approach

A computer-implemented method for pre-cropping digital image data to remove background from the digital image data, comprising:

• dividing the digital image into a plurality of segments;
• computing a color value distance between corresponding pixels of one or more pairs of neighboring segments of the digital image;
• comparing the color value distance computed for some or all of the pairs of neighboring segments against a minimum color distance threshold;
• clustering all pairs of neighboring segments having a color value distance less than or equal to the minimum color distance threshold;
• computing a connected structure based on a shape of the clustered segments;
• computing a polygon bounding the connected structure;
• comparing a fraction of segments included in both the connected structure and the polygon, relative to a total number of segments in the digital image, to a minimum included segment threshold;
• and
• in response to determining the fraction of segments included in both the connected structure and the polygon, relative to the total number of segments in the digital image meets or exceeds a minimum included segment threshold, cropping the digital image based on edges of the polygon.