Swapping Gender is a Snap(chat)

In May 2019 the photographic cellphone application Snapchat released two company-generated image filters that were officially dubbed “My Twin” and “My Other Twin,” though users and media labeled them as feminine and masculine, respectively. While touted in most commentary as a “gender swap” feature, these digital imaginaries represent a unique opportunity to consider what features contribute to classification of faces into binary gender buckets. After all, the commonly considered “male” filter makes various modifications—including a broader jaw and addition of facial hair—to whichever face is selected in the photograph. It does not ask and cannot detect if that face belongs to a man or woman (cis- or transgender) or to a non-binary individual. Instead, the augmented reality that it offers is a preprogrammed algorithmic reinscription of reductive gendered norms. When interacting with a novel face, humans similarly implement algorithms to assign a gender to that face. The Snapchat “My Twin” filters—which are not neutral, but rather human-designed—offer an analyzable projection of one such binarization, which is otherwise rarely articulated or visually recreated. Here I pair an ethnographic exploration of twenty-eight transgender, non-binary, and/or gender diverse individuals’ embodied experiences of facial gender legibility throughout life and with digital distortion, with a quantitative analysis of the “My Twin” filter facial distortions, to better understand the role of technology in reimaginations of who and what we see in the mirror.

Fast and faithful scale-aware image filters

This paper proposes a fast and accurate computational framework for scale-aware image filters. Our framework is based on accurately approximating $$L^{1}$$ L 1 Gaussian convolution with respect to a transformed pixel domain representing geodesic distance on a guidance image manifold in order to recover salient edges in a manner faithful to scale-space theory while removing small image structures. Our framework possesses linear computational complexity with high approximation precision. We examined it numerically in terms of speed, accuracy, and quality compared with conventional methods.

Digital image filters are not necessarily related to improvement in diagnostic of degenerative bone changes in the temporomandibular joint on cone beam computed tomography

This study assessed whether the use of digital image filters influences the detection of temporomandibular joint (TMJ) bone changes on cone beam computed tomography (CBCT). Two radiologists evaluated the TMJ images of CBCT scans to verify the presence of osteophytes, erosions, pseudocysts, bone sclerosis and flattening, using the software XoranCAT®; each image of the TMJ was assessed with and without the use of the following filters: Angio Sharpen 3x3 and Angio Sharpen 5x5. Kruskal-Wallis’ test was used to assess whether the application of filters influenced the scores assigned to the degenerative bone changes in the condyle. Flattening was present in 15 cases (51.72%), followed by osteophytes in six cases (20.69%), sclerosis in three cases (10.34%), and erosion in three cases (10.34%), with pseudocyst found in two cases (6.90%). No statistically significant difference was found in the scores (P = 0.786) regarding the original images and those treated with both filters. Digital image filters used in our study did not influence the diagnosis of degenerative bone changes in the TMJ on CBCT images.

Two iterative methods for reverse image filtering

We consider the problem of recovering an original image $${\varvec{x}}$$ x from its filtered version $${\varvec{y}}={\varvec{f}}({\varvec{x}})$$ y = f ( x ) , assuming that the internal structure of the filter $${\varvec{f}}(\cdot )$$ f ( · ) is unknown to us (i.e., we can only query the filter as a black-box and, for example, cannot invert it). We present two new iterative methods to attack the problem, analyze, and evaluate them on various smoothing and edge-preserving image filters.

Effect of Deep Learning Feature Inference Techniques on Respiratory Sounds

Analysis of respiratory sounds increases its importance every day. Many different methods are available in the analysis, and new techniques are continuing to be developed to further improve these methods. Features are extracted from audio signals and trained using different machine learning techniques. The use of deep learning, which is a different method and has increased in recent years, also shows its influence in this field. Deep learning techniques applied to the image of audio signals give good results and continue to be developed. In this study, image filters were applied to the values obtained from audio signals and the results of the features formed from this were examined in machine learning and deep learning techniques. Their results were compared with the results of methods that had previously achieved good results.

High-Performance Image Filters via Sparse Approximations

We present a numerical optimization method to find highly efficient (sparse) approximations for convolutional image filters. Using a modified parallel tempering approach, we solve a constrained optimization that maximizes approximation quality while strictly staying within a user-prescribed performance budget. The results are multi-pass filters where each pass computes a weighted sum of bilinearly interpolated sparse image samples, exploiting hardware acceleration on the GPU. We systematically decompose the target filter into a series of sparse convolutions, trying to find good trade-offs between approximation quality and performance. Since our sparse filters are linear and translation-invariant, they do not exhibit the aliasing and temporal coherence issues that often appear in filters working on image pyramids. We show several applications, ranging from simple Gaussian or box blurs to the emulation of sophisticated Bokeh effects with user-provided masks. Our filters achieve high performance as well as high quality, often providing significant speed-up at acceptable quality even for separable filters. The optimized filters can be baked into shaders and used as a drop-in replacement for filtering tasks in image processing or rendering pipelines.

Oil spill identification in visible sensor imaging using automated cross correlation with crude oil image filters

An algorithm for detection of crude oil spills in visible light images has been developed and tested on 50 documented crude oil spill images from Shell Petroleum Development Company (SPDC) Nigeria. A set of three 25 x 25 pixels crude oil filters, with unique red, green, and blue (RGB) colour values, homogeneity, and power spectrum density (PSD) features were cross-correlated with the documented spill images. The final crude oil spill Region of Interest (ROI) was determined by grouping interconnected pixels based on their proximity, and only selecting ROIs with an area greater than 5,000 pixels. The crude oil filter cross correlation algorithm demonstrated a sensitivity of 84% with a False Positive per Image (FPI) of 0.82. Future work includes volume estimation of detected spills using crude oil filters, and utilizing this information in the recommendation of appropriate spill clean-up and remediation procedures for the detected spills. Keywords: Crude Oil Spill Detection, Crude oil image filters, Cross correlation, Visible sensor imaging, Oil Spill Segmentation.