As part of the cancer drug development process, evaluation in experimental subcutaneous tumour transplantation models is a key process. This involves implanting tumour material underneath the mouse skin and measuring tumour growth using calipers. This methodology has been proven to have poor reproducibility and accuracy due to observer variation. Furthermore the physical pressure placed on the tumour using calipers is not only distressing for the mouse but could also lead to tumour damage. Non-invasive digital imaging of the tumour would reduce handling stresses and allow volume determination without any potential tumour damage. This is challenging as the tumours sit under the skin and have the same colour pattern as the mouse body making them hard to differentiate in a 2D image. We used the pre-trained convolutional neural network VGG-16 and extracted multiple layers in an attempt to accurately locate the tumour. When using the layer FC7 after RELU activation for extraction, a recognition rate of 89.85% was achieved.

Color correction relates device-dependent sensor responses (RGB) to device independent color values ($XYZ$). Here, we present a new approach to Hue-plane preserving color correction (HPPCC) using weighted constrained$3 \times 3$matrices. Hue-plane preservation was introduced in[1]in conjunction with an HPPCC method. That method maps using a finite number of local white point preserving$3 \times 3$matrices, each of which operates in a Hue-angle delimited subregion of device space defined by the white and two adjacent chromatic training set colors. However, that formulation does not leave room for optimization or continuity beyond$C^{0}$in the transitions between the subregions. To remedy that, our new method uses Hue-angle specific weighted matrixing: given a device RGB from which a device Hue-angle is derived, a corresponding transformation matrix is found as the normalized weighted sum of all precalculated constrained white point and training color preserving matrices. Each weight is calculated as a power function of the minimum difference between the device and the training color Hue-angle. The weighting function provides local influence to the matrices that are in close Hue-angle proximity to the device color. The power of the function is optimized for global accuracy. We call this HPPCC by weighted constrained matrixing.1Experiments performed using different input spectra show that our method consistently improves on both stability and accuracy compared with the state-of-the-art methods.1Patent Pending: PCT/2015/000054

In computer vision, there are many applications, where it is advantageous to process an image in the gradient domain and then reintegrate the gradient field: important examples include shadow removal, lightness calculation, and data fusion. A serious problem with this approach is that the reconstruction step often introduces artefacts-commonly, smoothed and smeared edges-to the recovered image. This is a result of the inherent ill-posedness of reintegrating a nonintegrable field. Artefacts can be diminished but not removed, by using complex to highly complex reintegration techniques. Here, we present a remarkably simple (and on the face of it naive) algorithm for reconstructing gradient fields. Suppose we start with a multichannel original, and from it derive a (possibly one of many) 1-D gradient field; for many applications, the derived gradient field will be nonintegrable. Here, we propose a lookup-table-based map relating the multichannel original to a reconstructed scalar output image, whose gradient best matches the target gradient field. The idea, at base, is that if we learn how to map the gradients of the multichannel original onto the desired output gradient, and then using the lookup table (LUT) constraint, we effectively derive the mapping from the multichannel input to the desired, reintegrated, image output. While this map could take a variety of forms, here we derive the best map from the multichannel gradient as a (nonlinear) function of the input to each of the target scalar gradients. In this framework, reconstruction is a simple equation-solving exercise of low dimensionality. One obvious application of our method is to the image-fusion problem, e.g., the problem of converting a color or higher-D image into grayscale. We will show, through extensive experiments and complementary theoretical arguments, that our straightforward method preserves the target contrast as well as do complex previous reintegration methods, but without artefacts, and with a substantially cheaper computational cost. Finally, we demonstrate the generality of the method by applying it to gradient field reconstruction in an additional area, the shading recovery problem.