Automatic background detection of scanned documents
View Patent ↗A background detection process that analyzes background information for the purpose of limiting the impact of intensity information obtained from non-document areas includes: identifying a first white peak from pixels within a first document region; identifying a second white peak from pixels within a second document region; determining if the first white peak was identified using image data from outside of the input document; and if so, identifying a third white peak from pixels within the first document region based on the second white peak.
1. A method for generating a background peak for a scanned document, comprising:
generating a first histogram from pixels within a first document region, the first document region representing a full page;
generating a second histogram from pixels within a second document region;
identifying a first white peak from the first histogram;
identifying a second white peak from the second histogram;
comparing a width of the first white peak to a width threshold;
comparing the first white peak to at least one of a minimum threshold, a maximum threshold, and a threshold generated as a function of the second white peak; and
identifying a third white peak from within a range of the first histogram defined by a function of the first white peak and by a function of the second white peak.
2. The method according to claim 1 , wherein:
the function of the first white peak adds a first offset value to the first peak to set an upper limit; and
the function of the second white peak adds a second offset value to the second peak to set a lower limit.
3. The method according to claim 2 , further comprising determining a background level for the scanned document based on the third white peak.
4. A method of determining a background statistic for a scanned input document, comprising the steps of:
identifying a first white peak from pixels within a first document region;
identifying a second white peak from pixels within a second document region;
determining if the first white peak was identified using image data from outside of the input document; and
if so, identifying a third white peak from pixels within the first document region based on the second white peak, wherein a lower search limit of a range to search for a peak is set as a sum of an offset margin value and the second white peak.
5. The method according to claim 4 , wherein the step of identifying a third white peak further comprises setting the value of the third white peak to equal to a function of the second white peak when a white peak is not detected within a range.
6. The method according to claim 4 , further comprising determining a background level for the scanned document based on the third white peak.
7. The method according to claim 4 , wherein the step of determining if the first white peak was identified using image data from outside of the input document comprises:
analyzing the first white peak using at least one of the following comparisons: comparing the first white peak to a minimum threshold; comparing the first white peak to a maximum threshold; comparing the first white peak to a threshold generated as a function of the second white peak; and comparing a width of the first white peak to a width threshold.
8. A method of determining a background statistic for a scanned input document, comprising the steps of:
identifying a first white peak from pixels within a first document region, the first document region representing a full page;
identifying a second white peak from pixels within a second document region, the second document region comprising a subset of the first document region;
determining if the first white peak was identified using image data from outside of the input document; and
if so, identifying a third white peak from pixels within the first document region, wherein a limit of a range to search for the third peak is set as a sum of an offset margin value and the second white peak.
9. The method according to claim 8 , wherein the step of identifying a third white peak further comprises selling the value of the third white peak to equal to a function of the second white peak when a white peak is not detected within the range to search.
10. The method according to claim 9 , wherein the second document region corresponds to a document lead edge.
11. The method according to claim 8 , further comprising determining a background level for the scanned document based on the third white peak.
12. The method according to claim 8 , wherein the step of determining if the first white peak was identified using image data from outside of the input document comprises comparing the first white peak at least one of a minimum threshold; a maximum threshold; a threshold generated as a function of the second white peak; and a peak width threshold.