Prediction-based ovarian follicle detection
Coordinators: B. Potočnik and D. Zazula
Our previous approach introduced a new algorithm for object detection on a single static image from an image sequence. This algorithm extends the basic 2D recognition scheme by incorporating knowledge about previous image recognition. A new algorithm is presented for object recognition from an image sequence using prediction procedures. It is based on the Kalman filter. The measurement system is realized with an algorithm for static 2D images. An object model is set based on measurements in the first image of sequence. This model is modified from image to image using the Kalman filter in regard to new measurements. This model calculated for a particular image defines a new best estimate of the object searched for. This prediction algorithm was tested on sequences of ovarian ultrasound images with follicles. The obtained results are much more compact and accurate using the prediction algorithm than with the 2D algorithm only (up to 30 % according to the initial values). The number of misidentified follicles is considerably lower (up to 75 %). It points out that when using such processing of image sequences, the reliability of the obtained results is greatly increased.
Fig. 1: Some typical results on the real images. The left image of each row of images presents follicles as recognised using prediction algorithm, and the right one, the follicle position as encircled by an expert.
B. Potocnik and D. Zazula, "Automated Analysis of a Sequence of Ovarian Ultrasound Images, Part II: Prediction-Based Object Recognition from a Sequence of Images", Image and Vision Computing, 2000, submitted.
B. Potocnik, "Razpoznavanje objektov iz zaporedja slik s postopki predikcije (Prediction-based object recognition from a sequence of images)", PhD thesis, 2000, University of Maribor, Faculty of EE and CS, Maribor. (in Slovene)
B. Potocnik, PhD defense , september 2000, Maribor. (in Slovene)