In this study, the authors propose a novel method to encrypt a colour image by use of Logistic mapping and double random-phase encoding. Firstly, use Logistic mapping to diffuse the colour image, then the red, green and blue components of the result are scrambled by replacement matrices generated by Logistic mapping. Secondly, by utilising double random-phase encoding to encrypt the three scrambled images into one encrypted image. Experiment results reveal the fact that the proposed method not only can achieve good encryption result, but also that the key space is large enough to resist against common attack.

A variant of fuzzy c-means (FCM) clustering algorithm for image segmentation is provided. Unlike the -norm distance in FCM, with norm is used to measure the distance of the pixel intensity to its cluster centre in the energy functional. Moreover, local spatial information and colour information are incorporated into the model to enhance the robustness to noise and outliers. The proposed algorithm is called fuzzy local information (FLILp) clustering. To overcome the difficulty of finding cluster centres, -norm distance is approximated by weighted distance. The advantages of FLILp are: (i) it is strongly robust to noise and outliers, (ii) it is applied to the original image and (iii) it preserves image edges. Numerical examples and comparisons of image segmentation on both synthetic and real images illustrate the outstanding performance and robustness of the proposed method.

It is significant to extract rotation, scaling, translation, and noise (RSTN) invariant features inspired by biological vision for image recognition. A bionic RSTN-invariant feature extraction are proposed. This extraction process comprises two stages. In the first stage, a novel orientation edge detection is designed based on a filter-to-filter scheme. Gabor filters, a bottom filter, smoothen an image by simulating biological vision. Bipolar filters, a top filter, detect the horizontal and vertical direction orientation edge by simulating vision cortex response. After obtaining the orientation edge of the image, an interval detector is executed by a spatial frequency of different direction and distance. Then, the interval detection results are transformed into pixels of the orientation-interval feature map. RSTN invariant features are generated through the repetition of orientation edge detection and interval detection. Several experimental results demonstrate that RSTN-invariant features have striking robustness, and capable to classify RSTN images. Finally, bionic invariant features are practiced in traffic sign recognition.

To help the clinicians to segment the borders of the left ventricle (LV) efficiently during measurement of the heart, the authors come up with a semi-automatic approach in this study that is capable of identifying the endocardial borders robustly from cine magnetic resonance images. Firstly, the deformation flow is computed between the inputted boundary in the previous frame and the extracted edge of the LV in the current frame based on boundary minimum distance principle (BMDP). Then, the deformation flow is constrained by optical flow calculated by a partial differential equation model. A smooth deformation boundary is then formed by minimising the energy between the previously inputted boundary and the rough boundary obtained by BMDP and optical flow constraint. To extract edge of the LV as accurate as possible, a threshold selection method is used and improved based on the previous study. The proposed approach is tested on the open access dataset. The computed average perpendicular distance is 1.36 ± 0.24 mm and the computed Dice measure is 90.7% ± 0.15%. Experimental results show that the proposed approach is significantly more accurate than the referenced state of art methods.

Rate control (RC) plays a critical role in video coding for regulating the coded bit-stream to achieve the target bitrate, which involves two basic steps: bit allocation (BA) and quantisation parameter selection. Here, the former is a key element to directly affect the performance of RC. So, in this study, an efficient frame-level BA algorithm is proposed for the latest video coding standard H.265/high-efficiency video coding (HEVC). First, by analysing the optimisation problem of the frame-level BA, two factors have been found to be related to the frame-level BA, which are inter-frame dependency and the target bitrate. Then, a measure of inter-frame dependency is put forward to reflect the correlation among consecutive frames. Finally, according to the results of allocation weights through the dynamic programming method, the relationships among the allocation weights and the two factors are investigated, and based on which the efficient BA model is established. Experimental results show that in comparison with the original RC scheme in HM-14.0, the proposed frame-level BA algorithm reduces, on average, BD-rate by 5.19% with negligible encoding time increase. In addition, the proposed algorithm also achieves higher GOP-level RC accuracy compared with the original RC scheme in HM.

Automatic identification of abnormal cervical cells, including feature representation, feature combination and classification strategy, is highly demanded in women's annual cervical cancer screenings. However, previous methods only deal with one or two of these three phases, and currently there is few complete framework for this problem. A novel three-phrase boosting framework is proposed for the detection of abnormal cells from cervical smear images. First, the authors extract 160 dimensional features with respect to each cervical cell from three aspects, including cytology morphology, chromatin pathology and region intensity. In particular, 106 dimensional chromatin pathology features are newly adopted to describe the nucleus textural transformation. Second, an adaptive feature combination method is introduced to select the optimal feature patterns, which can combine all features using a reinforced margin-based approach with the heuristic knowledge. Finally, a two-stage classification strategy is presented to reduce erroneous classification abnormal cells using two different classifiers. Experimental results achieve state-of-the-art performance and the proposed framework outperforms the other 16 compared detection methods.

Hyperspectral face recognition provides improved classification rates due to its abundant information in the face cubes of every subject in hyperspectral face databases. However, it is less popular in face recognition due to its difficulty in data acquisition, low signal-to-noise ratio, and high dimensionality. The authors compare five existing descriptors that are frequently used in 2D face recognition, and use collaborative representation classifier (CRC) with two voting techniques for hyperspectral face recognition. Experimental results demonstrate that, for PolyU-HSFD database, Gabor filter bank-based features are very robust to both Gaussian white noise and shot noise, and it achieves very competitive classification results. For CMU-HSFD database, when the noise level is low, histogram of oriented gradients (HOG) yields good classification results. In addition, when the noise level is high, raw facial images without feature extraction perform very well in term of correct classification rate. The local binary pattern and HOG descriptor are very sensitive to noise even though they achieve rather good classification rates if the facial images contain no noise. The best recognition result for the PolyU-HSFD is 96.4% ± 2.3 and for the CMU-HSFD is 98.0% ± 0.7.