Method for efficient coding of shape descriptor parameters
A method of representing an object appearing in a still or video image, by processing signals corresponding to the image, comprises deriving a plurality of sets of co-ordinate values representing the shape of the object and quantising the co-ordinate values to derive a coded representation of the shape, and further comprises quantising a first co-ordinate value over a first quantisation range and quantising a smaller co-ordinate value over a smaller range.
1. A method of representing an object appearing in an image or sequence of images, by processing signals corresponding to the image, the method comprising:
deriving a curvature scale space (CSS) representation of the shape of the object;
deriving a plurality of sets of co-ordinate values, the sets of co-ordinate values corresponding to peaks of the CSS representation;
ordering the plurality of sets of co-ordinate values in decreasing order of the peak height component values;
quantizing the co-ordinate values to derive a coded representation of the shape, where the range over which a given co-ordinate value is quantised-is based on the value of the preceding peak height component value; and
storing the coded representation of the shape.
2. A method as claimed in claim 1 wherein the number of bits allocated to the quantised representation of a peak height component value is less than the number of bits allocated to the quantised representation of a preceding peak height component value.
3. A method as claimed in claim 1 wherein the number of bits allocated to the quantised representation of a peak height component value is same as the number of bits allocated to the quantised representation of a preceding peak height component value.
4. An apparatus for deriving coded representations of the shape of an object in an image or sequence of images, comprising:
a processor configured to
derive a curvature scale space (CSS) representation of the shape of the object;
derive a plurality of sets of co-ordinate values, the sets of co-ordinate values corresponding to peaks of the CSS representation;
order the plurality of sets of co-ordinate values in decreasing order of the peak height component values; and
quantise the co-ordinate values to derive a coded representation of the shape, where the range over which a given co-ordinate value is quantized is based on the value of the preceding peak height component value; and
memory for storing the coded representation of the shape.
5. The apparatus of claim 4 , further comprising:
a display.
6. The apparatus of claim 4 , further comprising:
a pointing device.
7. A computer readable medium having stored thereon a computer program for deriving coded representations of the shape of an object in an image or sequence of images, which when executed causes a computer system to carryout the steps of:
deriving a curvature scale space (CSS) representation of the shape of the object;
deriving a plurality of sets of co-ordinate values, the sets of co-ordinate values corresponding to peaks of the CSS representation;
ordering the plurality of sets of co-ordinate values in decreasing order of the peak height component values;
quantising the co-ordinate values to derive a coded representation of the shape, where the range over which a given co-ordinate value is quantized is based on the value of the preceding peak height component value; and
storing the coded representation of the shape.