Underwater Fish Segmentation Algorithm Based on Improved PSPNet Network.

With the sustainable development of intelligent fisheries, accurate underwater fish segmentation is a key step toward intelligently obtaining fish morphology data. However, the blurred, distorted and low-contrast features of fish images in underwater scenes affect the improvement in fish segmentation accuracy. To solve these problems, this paper proposes a method of underwater fish segmentation based on an improved PSPNet network (IST-PSPNet). First, in the feature extraction stage, to fully perceive features and context information of different scales, we propose an iterative attention feature fusion mechanism, which realizes the depth mining of fish features of different scales and the full perception of context information. Then, a SoftPool pooling method based on fast index weighted activation is used to reduce the numbers of parameters and computations while retaining more feature information, which improves segmentation accuracy and efficiency. Finally, a triad attention mechanism module, triplet attention (TA), is added to the different scale features in the golden tower pool module so that the space attention can focus more on the specific position of the fish body features in the channel through cross-dimensional interaction to suppress the fuzzy distortion caused by background interference in underwater scenes. Additionally, the parameter-sharing strategy is used in this process to make different scale features share the same learning weight parameters and further reduce the numbers of parameters and calculations. The experimental results show that the method presented in this paper yielded better results for the DeepFish underwater fish image dataset than other methods, with 91.56% for the Miou, 46.68 M for Params and 40.27 G for GFLOPS. In the underwater fish segmentation task, the method improved the segmentation accuracy of fish with similar colors and water quality backgrounds, improved fuzziness and small size and made the edge location of fish clearer.

The use of telomeric length as authenticity marker in fish and seafood - a new perspective in the detection of adulteration.

In this review we propose the use of telomeric length (TL) as an authenticity marker that could provide an alternative method for differentiating fish and seafood samples or detecting fraud. Considering the ever-growing number of incidents of economically motivated fish and seafood adulteration using even more sophisticated methods to overcome current authenticity markers, the need to identify novel authenticity markers becomes essential. The TL of fish and seafood depends on individual characteristics (e.g., sex, age) and the environmental stimuli (e.g., temperature, water quality) to which these are exposed. Hence, both wild marine and freshwater populations occupying different geographical origin habitats might differ substantially because of the environmental cues affecting them. Moreover, the implementation of various rearing practices in aquaculture, such as different levels of fish and seafood density and increased ambient noise combined with site-specific environmental cues could affect TL, providing regulatory authorities with valuable information by distinguishing wild from reared populations and organic from conventional ones. In the present review the effects of both the environmental conditions and individual characteristics on the telomeric stability of fish and seafood telomeres are discussed, suggesting TL as a potential prospect authenticity marker that could be used to prevent fish and seafood adulteration.

Mercury accumulation in marine fish most favoured by Malaysian women, the predictors and the potential health risk.

We identified marine fish species most preferred by women at reproductive age in Selangor, Malaysia, mercury concentrations in the fish muscles, factors predicting mercury accumulation and the potential health risk. Nineteen most preferred marine fish species were purchased (n = 175) from selected fisherman's and wholesale market. Length, weight, habitat, feeding habit and trophic level were recognised. Edible muscles were filleted, dried at 80 °C, ground on an agate mortar and digested in Multiwave 3000 using HNO3 and H2O2. Total mercury was quantified using VP90 cold vapour system with N2 carrier gas. Certified reference material DORM-4 was used to validate the results. Fish species were classified as demersal (7) and pelagic (12) or predators (11), zoo benthos (6) and planktivorous (2). Length, weight and trophic level ranged from 10.5 to 75.0 cm, 0.01 to 2.50 kg and 2.5 to 4.5, respectively. Geometric mean of total mercury ranged from 0.21 to 0.50 mg/kg; maximum in golden snapper (0.90 mg/kg). Only 9 % of the samples exceeded the JECFA recommendation. Multiple linear regression found demersal, high trophic (≥4.0) and heavier fishes to accumulate more mercury in muscles (R 2 = 27.3 %), controlling for all other factors. About 47 % of the fish samples contributed to mercury intake above the provisional tolerable level (45 µg/day). While only a small portion exceeded the JECFA fish Hg guideline, the concentration reported may be alarming for heavy consumers. Attention should be given in risk management to avoid demersal and high trophic fish, predominantly heavier ones.