Compressive Sensing is an alternative to the acquisition and compression of sparse signals. One of the CS applications is the single pixel camera that reconsiders the conventional imaging systems. The key part of the camera is a Digital Micro-mirror Device (DMD), which is operated by a binary sensing matrix. The paper objective is to evaluate the CS performances in the case of three different binary sensing matrices - Binary Random (BRandom), Binary Sparse (BSparse) and Low Density Parity Check (LDPC) code - and three sparsifying transforms: Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT) and Total Variation (TV). The study concerns numeric images and it is done from the perspective of the Rate-Distortion characteristic. The experimental results indicate the couple LDPC - TV as the best solution and proves that visually lossless compression can be obtained by this approach.