Comparison of Image Transform-Based Features for Visual Speech Recognition in Clean and Corrupted Videos

We present results of a study into the performance of a variety of different image transform-based feature types for speaker-independent visual speech recognition of isolated digits. This includes the first reported use of features extracted using a discrete curvelet transform. The study will show a comparison of some methods for selecting features of each feature type and show the relative benefits of both static and dynamic visual features. The performance of the features will be tested on both clean video data and also video data corrupted in a variety of ways to assess each feature type's robustness to potential real-world conditions. One of the test conditions involves a novel form of video corruption we call jitter which simulates camera and/or head movement during recording.

A comparative assessment of potential components of partial disease resistance to Fusarium head blight detected in a detached leaf assay of wheat, barley and oats.

The relative resistance of 15 winter barley, three winter wheat and three winter oat cultivars on the UK recommended list 2003 and two spring wheat cultivars on the Irish 2003 recommended list were evaluated using Microdochium nivale in detached leaf assays to further understand components of partial disease resistance (PDR) and Fusarium head blight (FHB) resistance across cereal species. Barley cultivars showed incubation periods comparable to, and latent periods longer than the most FHB resistant Irish and UK wheat cultivars evaluated. In addition, lesions on barley differed from those on wheat as they were not visibly chlorotic when placed over a light box until sporulation occurred, in contrast to wheat cultivars where chlorosis of the infected area occurred when lesions first developed. The pattern of delayed chlorosis of the infected leaf tissue and longer latent periods indicate that resistances are expressed in barley after the incubation period is observed, and that these temporarily arrest the development of mycelium and sporulation. Incubation periods were longer for oats compared to barley or wheat cultivars. However, oat cultivars differed from both wheat and barley in that mycelial growth was observed before obvious tissue damage was detected under macroscopic examination, indicating tolerance of infection rather than inhibition of pathogen development, and morphology of sporodochia differed, appearing less well developed and being much less abundant. Longer latent periods have previously been related to greater FHB resistance in wheat. The present results suggest the longer latent periods of barley and oat cultivars, than wheat, are likely to play a role in overall FHB resistance if under the same genetic control as PDR components expressed in the head. However the limited range of incubation and latent periods observed within barley and oat cultivars evaluated was in contrast with wheat where incubation and latent periods were shorter and more variable among genotypes. The significance of the various combinations of PDR components detected in the detached leaf assay as components of FHB resistance in each crop requires further investigation, particularly with regard to the apparent tolerance of infection in oats and necrosis in barley, after the incubation period is observed, associated with retardation of mycelial growth and sporulation.