Fig 2 - uploaded by Boguslaw Cyganek
Content may be subject to copyright.
Approximation of the S function with the two quadratic functions defined from x min to 0 and from 0 to x max .
Source publication
Computationally Efficient Methods of Approximations of the S-Shape Functions for Image Processing and Computer Graphics Tasks
The paper describes a number of methods for approximation of the S-shape functions, frequently used in computer graphics or image processing. The main focus is on efficient software and hardware implementations. We present o...
Contexts in source publication
Context 2
... ρ z reaches its minimum which is z=0. Parameter ρ can take on the following values: 0, 1, 2, … Such representation was chosen to allow simple implementation, as will be shown later in this section. An additional parameter is a slope of the curve in the point x=0. This can be found after differentiation of (4) at a point x=0, which is as follows (Fig. ...
Similar publications
The dictionary approach to signal and image processing has been massively investigated in the last two decades, proving very attractive for a wide range of applications. The effectiveness of dictionary-based methods, however, is strongly influenced by the choice of the set of basis functions. Moreover the structure of the dictionary is of paramount...
Citations
... For example in [7], a generalized form of the function is applied to predict the site index of unmanaged loblolly and slash pine plantations in East Texas. Furthermore, it also applied in computer graphics or image processing to enhance image contrast (see [8], [12]). ...
By using some analytical techniques, we establish some properties of the sigmoid function. The properties are in the form of inequalities involving the function. Some of these inequalities connect the sigmoid function to the softplus function.
This work presents a low power radiation detection and radioisotope identification system-on-chip (SoC) featuring mixed-signal sensory electronics and on-chip neural network (NN) acceleration hardware. The chip electronics form a multichannel analyzer (MCA) to process the signal from an external radiation detector and produce an energy spectrum of the incoming radiation detections. The neural network hardware accelerator then provides a novel means of using the spectrum to perform radioisotope identification. The chip is thus able to determine which radioisotopes are present in the radiation source. An on-chip 32-bit microcontroller (MCU) configures the analog front-end (AFE) electronics, oversees the NN hardware, and provides an interface to retrieve the histogram and NN data. The chip is fabricated on a 65 nm CMOS technology and consumes 8.8 mW while acquiring a histogram. In the tested configuration, the radioisotope identification neural network takes 694 μs to execute, consuming 1.94 μJ of energy and using 13.8 KB of RAM in the process. After training, the system correctly identified which isotopes were present in all histograms in a test set composed of combinations of four trained isotopes.
